ggplot2-条形图和折线图

我不是女神ヾ 2022-12-02 15:09 303阅读 0赞

一个比较好的ggplot学习博文

> author: 李丕栋  
> email: hope-dream@163.com  
> date: 2016年3月7日

[http://blog.csdn.net/tanzuozhev/article/details/50822204][http_blog.csdn.net_tanzuozhev_article_details_50822204]

本文在 [http://www.cookbook-r.com/Graphs/Bar\_and\_line\_graphs\_(ggplot2)][http_www.cookbook-r.com_Graphs_Bar_and_line_graphs_ggplot2] 的基础上加入了自己的理解.  
ggplot2 接受的数据类型必须为data.frame结构,

### 离散数据作为x轴 ###

对于条形图, 对于高度的设置有两种不同的选择:

1.  x,y 对应的数值为实际的图上数值, x为横轴标签,y为纵轴高度.这时候使用`geom_bar(stat="identity")`作为图层.

library(ggplot2)
    dat <- data.frame(
      time = factor(c("Lunch","Dinner"), levels=c("Lunch","Dinner")),
      total_bill = c(14.89, 17.23)
    )
    dat
     
      
     
      
       1
       2
       3
       4
       5
       6

## time total_bill
    ## 1 Lunch 14.89
    ## 2 Dinner 17.23
     
      
     
      
       1
       2
       3

`time`列为因子型变量, 表示x轴标签和填充颜色  
`total_bill` 列为y轴的实际数值, 表示高度

ggplot(data=dat, aes(x=time, y=total_bill)) +
        geom_bar(stat="identity")
     
      
     
      
       1
       2

![20160307203034776][]

# 以time作为颜色填充
    ggplot(data=dat, aes(x=time, y=total_bill, fill=time)) +
        geom_bar(stat="identity")
     
      
     
      
       1
       2
       3

![20160307203407420][]

## 等同于
     ggplot(data=dat, aes(x=time, y=total_bill)) +
        geom_bar(aes(fill=time), stat="identity")
     
      
     
      
       1
       2
       3

![这里写图片描述][20160307203445403]

# 添加黑色轮廓线
    ggplot(data=dat, aes(x=time, y=total_bill, fill=time)) +
        geom_bar(colour="black", stat="identity")
     
      
     
      
       1
       2
       3

![这里写图片描述][20160307203529575]

# 去除图例
    ggplot(data=dat, aes(x=time, y=total_bill, fill=time)) +
        geom_bar(colour="black", stat="identity") +
        guides(fill=FALSE)
     
      
     
      
       1
       2
       3
       4

![这里写图片描述][20160307203558966]

# 添加其他信息 title, narrower bars, fill color, and change axis labels
    ggplot(data=dat, aes(x=time, y=total_bill, fill=time)) + 
        geom_bar(colour="black", fill="#DD8888", width=.8, stat="identity") + 
        guides(fill=FALSE) +
        xlab("Time of day") + ylab("Total bill") +
        ggtitle("Average bill for 2 people")
     
      
     
      
       1
       2
       3
       4
       5
       6

![这里写图片描述][20160307203643454]

1.  输入一组数据,对于x轴与y轴的信息需要进行统计计数.x轴为数据去除重复项的保留值,y轴为x轴对应的重复次数.使用`geom_bar(stat="bin")`作为新图层.

# 使用reshape2包的tips数据集
    library(reshape2)
    # 数据展示
    head(tips)
     
      
     
      
       1
       2
       3
       4

## total_bill tip sex smoker day time size
    ## 1 16.99 1.01 Female No Sun Dinner 2
    ## 2 10.34 1.66 Male No Sun Dinner 3
    ## 3 21.01 3.50 Male No Sun Dinner 3
    ## 4 23.68 3.31 Male No Sun Dinner 2
    ## 5 24.59 3.61 Female No Sun Dinner 4
    ## 6 25.29 4.71 Male No Sun Dinner 4
     
      
     
      
       1
       2
       3
       4
       5
       6
       7

这里输入的变量只有x,没有y,x轴为day,要使用 `stat="bin"`代替 `stat="identity"`,数据去重后留下Sun Sat Thur Fri,它们对应的重复次数作为y轴.

# Bar graph of counts
    ggplot(data=tips, aes(x=day,fill=day)) +
        geom_bar(stat="bin")
     
      
     
      
       1
       2
       3

![这里写图片描述][20160307203720326]

## 等同于
    ggplot(data=tips, aes(x=day)) +
       geom_bar()# stat参数默认为 bin
     
      
     
      
       1
       2
       3

![这里写图片描述][20160307203742080]

### 折线图 ###

time: x-axis  
total\_bill: y-axis

# Basic line graph
    ggplot(data=dat, aes(x=time, y=total_bill, group=1)) +
        geom_line()
     
      
     
      
       1
       2
       3

![这里写图片描述][20160307203812128]

## This would have the same result as above
    # ggplot(data=dat, aes(x=time, y=total_bill)) +
    # geom_line(aes(group=1))
    
    # 折线图添加点
    ggplot(data=dat, aes(x=time, y=total_bill, group=1)) +
        geom_line() +
        geom_point()
     
      
     
      
       1
       2
       3
       4
       5
       6
       7
       8

![这里写图片描述][20160307203842249]

# 修改颜色
    # Change line type and point type, and use thicker line and larger points
    # Change points to circles with white fill
    ggplot(data=dat, aes(x=time, y=total_bill, group=1)) + 
        geom_line(colour="red", linetype="dashed", size=1.5) + 
        geom_point(colour="red", size=4, shape=21, fill="white")
     
      
     
      
       1
       2
       3
       4
       5
       6

![这里写图片描述][20160307203905676]

# Change the y-range to go from 0 to the maximum value in the total_bill column,
    # and change axis labels
    # 修改y轴的范围,从0到最大值
    ggplot(data=dat, aes(x=time, y=total_bill, group=1)) +
        geom_line() +
        geom_point() +
        expand_limits(y=0) +# 修改y轴的范围,从0到最大值 expand_limits(y = c(1, 9)),y从1到9
        xlab("Time of day") + ylab("Total bill") +
        ggtitle("Average bill for 2 people")
     
      
     
      
       1
       2
       3
       4
       5
       6
       7
       8
       9

![这里写图片描述][20160307203955781]

## 更多数据变量 ##

新建数据,这里增加了一个变量sex

dat1 <- data.frame(
        sex = factor(c("Female","Female","Male","Male")),
        time = factor(c("Lunch","Dinner","Lunch","Dinner"), levels=c("Lunch","Dinner")),
        total_bill = c(13.53, 16.81, 16.24, 17.42)
    )
    dat1
     
      
     
      
       1
       2
       3
       4
       5
       6

## sex time total_bill
    ## 1 Female Lunch 13.53
    ## 2 Female Dinner 16.81
    ## 3 Male Lunch 16.24
    ## 4 Male Dinner 17.42
     
      
     
      
       1
       2
       3
       4
       5

### 条形图 ###

变量映射  
time: x-axis  
sex: color fill  
total\_bill: y-axis.

# 这里涉及了几个图形的位置摆放
    # 默认为堆叠(Stacked bar graph) 
    ggplot(data=dat1, aes(x=time, y=total_bill, fill=sex)) +
        geom_bar(stat="identity")
     
      
     
      
       1
       2
       3
       4

![这里写图片描述][20160307205253615]

# 位置摆放, position_dodge()为分开摆放
    
    ggplot(data=dat1, aes(x=time, y=total_bill, fill=sex)) +
        geom_bar(stat="identity", position=position_dodge())
     
      
     
      
       1
       2
       3
       4

![这里写图片描述][20160307204025271]

# Change colors
    ggplot(data=dat1, aes(x=time, y=total_bill, fill=sex)) +
        geom_bar(stat="identity", position=position_dodge(), colour="black") +
        scale_fill_manual(values=c("#999999", "#E69F00"))# 修改填充的颜色,填充的颜色数组大小必须与fill(sex)的大小一致
     
      
     
      
       1
       2
       3
       4

![这里写图片描述][20160307205322428]

修改变量的映射,x轴为sex,颜色填充为time

# Bar graph, time on x-axis, color fill grouped by sex -- use position_dodge()
    ggplot(data=dat1, aes(x=sex, y=total_bill, fill=time)) +
        geom_bar(stat="identity", position=position_dodge(), colour="black")
     
      
     
      
       1
       2
       3

![这里写图片描述][20160307204054813]

### 折线图 ###

变量映射  
time: x-axis  
sex: line color  
total\_bill: y-axis.  
为了画出多条线,数据必须进行分组, 这里我们对`sex`进行分组,就会出现两条线,`Female`一条,`Male`一条.

# 简单图
    ggplot(data=dat1, aes(x=time, y=total_bill, group=sex)) +
        geom_line() +
        geom_point()
     
      
     
      
       1
       2
       3
       4

![这里写图片描述][20160307204125648]

# 加入颜色
    ggplot(data=dat1, aes(x=time, y=total_bill, group=sex, colour=sex)) +
        geom_line() +
        geom_point()
     
      
     
      
       1
       2
       3
       4

![这里写图片描述][20160307204153648]

# Map sex to different point shape, and use larger points
    ggplot(data=dat1, aes(x=time, y=total_bill, group=sex, shape=sex)) +
        geom_line() +
        geom_point()
     
      
     
      
       1
       2
       3
       4

![这里写图片描述][20160307204218290]

# Use thicker lines and larger points, and hollow white-filled points
    ggplot(data=dat1, aes(x=time, y=total_bill, group=sex, shape=sex)) + 
        geom_line(size=1.5) + 
        geom_point(size=3, fill="white") +
        scale_shape_manual(values=c(22,21))# 修改shape的类型 
     
      
     
      
       1
       2
       3
       4
       5

![这里写图片描述][20160307204247877]

修改变量的映射关系,按照time进行分组,Lunch一组,Dinner一组

ggplot(data=dat1, aes(x=sex, y=total_bill, group=time, shape=time, color=time)) +
        geom_line() +
        geom_point()
     
      
     
      
       1
       2
       3

![这里写图片描述][20160307204307392]

### 例子 ###

#### 条形图 ####

ggplot(data=dat1, aes(x=time, y=total_bill, fill=sex)) + 
        geom_bar(colour="black", stat="identity",
                 position=position_dodge(),
                 size=.3) +                        # Thinner lines
        scale_fill_hue(name="Sex of payer") +      # Set legend title
        xlab("Time of day") + ylab("Total bill") + # Set axis labels
        ggtitle("Average bill for 2 people") +     # Set title
        theme_bw()
     
      
     
      
       1
       2
       3
       4
       5
       6
       7
       8

![这里写图片描述][20160307204329901]

#### 折线图 ####

ggplot(data=dat1, aes(x=time, y=total_bill, group=sex, shape=sex, colour=sex)) + 
        geom_line(aes(linetype=sex), size=1) +     # Set linetype by sex
        geom_point(size=3, fill="white") +         # Use larger points, fill with white
        expand_limits(y=0) +                       # 设置x y轴的起止范围,这里是y从0开始
        scale_colour_hue(name="Sex of payer",      # Set legend title
                         l=30)  +                  # Use darker colors (lightness=30)
        scale_shape_manual(name="Sex of payer",
                           values=c(22,21)) +      # Use points with a fill color
        scale_linetype_discrete(name="Sex of payer") +
        xlab("Time of day") + ylab("Total bill") + # Set axis labels
        ggtitle("Average bill for 2 people") +     # Set title
        theme_bw() +                          # 设置主题
        theme(legend.position=c(.7, .4))           # 设置图例的位置
     
      
     
      
       1
       2
       3
       4
       5
       6
       7
       8
       9
       10
       11
       12
       13

![这里写图片描述][20160307204351417]

这幅折线图中, 使用了颜色`scale_colour_hue`,形状 `scale_shape_manual`,线型`scale_linetype_discrete`三种属性,应该有3个图例,但是因为图例的名称相同所以归为一类,如果三个图例的名称不同,就会出现3个图例.

ggplot(data=dat1, aes(x=time, y=total_bill, group=sex, shape=sex, colour=sex)) + 
        geom_line(aes(linetype=sex), size=1) +     # Set linetype by sex
        geom_point(size=3, fill="white") +         # Use larger points, fill with white
        expand_limits(y=0) +                       # 设置x y轴的起止范围,这里是y从0开始
        scale_colour_hue(name="Sex of payer1",      # Set legend title
                         l=30)  +                  # Use darker colors (lightness=30)
        scale_shape_manual(name="Sex of payer2",
                           values=c(22,21)) +      # Use points with a fill color
        scale_linetype_discrete(name="Sex of payer3") +
        xlab("Time of day") + ylab("Total bill") + # Set axis labels
        ggtitle("Average bill for 2 people") +     # Set title
        theme_bw() +                          # 设置主题
        theme(legend.position=c(.7, .4))           # 设置图例的位置
     
      
     
      
       1
       2
       3
       4
       5
       6
       7
       8
       9
       10
       11
       12
       13

![这里写图片描述][20160307204415658]

### 连续型数据做x轴 ###

新建数据

datn <- read.table(header=TRUE, text=' supp dose length OJ 0.5 13.23 OJ 1.0 22.70 OJ 2.0 26.06 VC 0.5 7.98 VC 1.0 16.77 VC 2.0 26.14 ')
     
      
     
      
       1
       2
       3
       4
       5
       6
       7
       8
       9

dose作为x轴, 这里dose为numeric,视为连续型变量

ggplot(data=datn, aes(x=dose, y=length, group=supp, colour=supp)) +
        geom_line() +
        geom_point()
     
      
     
      
       1
       2
       3

![这里写图片描述][20160307204518200]

当把dose作为连续型变量时,尽管dose只有 0.5, 1.0, 2.0 三类,x轴也必须显示0.5,1.0,1.5,2.0甚至更多的点.

### 离散型数据做x轴 ###

这里我们将dose数据转化为factor类型,就成了离散型, 0.5, 1.0, 2.0就只是单纯的类别名称.

# Copy the data frame and convert dose to a factor
    datn2 <- datn
    datn2$dose <- factor(datn2$dose)
    ggplot(data=datn2, aes(x=dose, y=length, group=supp, colour=supp)) +
        geom_line() +
        geom_point()
     
      
     
      
       1
       2
       3
       4
       5
       6

![这里写图片描述][20160307204544815]

# 直接在ggplot中转换格式也是可以的
    ggplot(data=datn, aes(x=factor(dose), y=length, group=supp, colour=supp)) +
        geom_line() +
        geom_point()
     
      
     
      
       1
       2
       3
       4

![这里写图片描述][20160307204602826]

连续型数据和离散型用于条形图, 得到了相同的图.

# Use datn2 from above
    ggplot(data=datn2, aes(x=dose, y=length, fill=supp)) +
        geom_bar(stat="identity", position=position_dodge())
     
      
     
      
       1
       2
       3

![这里写图片描述][20160307204622373]

# 直接使用factor转化
    ggplot(data=datn, aes(x=factor(dose), y=length, fill=supp)) +
        geom_bar(stat="identity", position=position_dodge())
     
      
     
      
       1
       2
       3

![这里写图片描述][20160307204646144]

[http_blog.csdn.net_tanzuozhev_article_details_50822204]: http://blog.csdn.net/tanzuozhev/article/details/50822204
[http_www.cookbook-r.com_Graphs_Bar_and_line_graphs_ggplot2]: http://www.cookbook-r.com/Graphs/Bar_and_line_graphs_%28ggplot2%29
[20160307203034776]: /images/20221123/15644961082e4a31bf23e3e680a5e85a.png
[20160307203407420]: /images/20221123/e293fd309f9942459ef581b03410ef86.png
[20160307203445403]: /images/20221123/6d062939b430494a9aa716ae31a68824.png
[20160307203529575]: /images/20221123/9e7d04dfc2d24a06b309bacb8d728e99.png
[20160307203558966]: /images/20221123/97c3b725d9bb48a7b1e240db1af664c9.png
[20160307203643454]: /images/20221123/36cc6548e2524c07ab95ad9e7815d399.png
[20160307203720326]: /images/20221123/7178fa6bdadf4cf2a549ed7e495fbb79.png
[20160307203742080]: /images/20221123/5ef32911001e4993b91414e243f0a326.png
[20160307203812128]: /images/20221123/1d2371fdd6394951ba0d5abe24c89450.png
[20160307203842249]: /images/20221123/310054ecd7c149f284352faf013baee9.png
[20160307203905676]: /images/20221123/9fc8d18ecbd44235b3193e900b85399c.png
[20160307203955781]: /images/20221123/363a1b5aaf5b4dadac003f63953199dd.png
[20160307205253615]: /images/20221123/0a9f2d486a3f46fb8f0c381ce57ad1c8.png
[20160307204025271]: /images/20221123/e7f0d7271b8649feb5fe7dc643ce1d1e.png
[20160307205322428]: /images/20221123/b9f87a62f36b464f9fd16358f7a4e87a.png
[20160307204054813]: /images/20221123/fabd5921f37b4456b3abf3362391bd2f.png
[20160307204125648]: /images/20221123/38bb8143a9ef43579e6c8f8706978945.png
[20160307204153648]: /images/20221123/3dc129ef7bff406d871fe44c4e35543e.png
[20160307204218290]: /images/20221123/be5712a644cf43e08ac6388a9a4a1ffd.png
[20160307204247877]: /images/20221123/da3c6238717941689865c19c7767b2cf.png
[20160307204307392]: /images/20221123/dc353d0f805146cb8e1a0e9316c10c99.png
[20160307204329901]: /images/20221123/bd87f6fca1e841b1a7ebe3065e17ff55.png
[20160307204351417]: /images/20221123/b837536c02304c658b4f947db88e6518.png
[20160307204415658]: /images/20221123/61d7f8d1563141788da77700c0bbffb2.png
[20160307204518200]: /images/20221123/daeb779a85c9471b97f54c8fb8ed92d9.png
[20160307204544815]: /images/20221123/409ad0093f9741b6b568402a0fc04972.png
[20160307204602826]: /images/20221123/699a34daea8841a1b17b7b9141f00eb6.png
[20160307204622373]: /images/20221123/7492976d79234444989df3b76b513cd6.png
[20160307204646144]: /images/20221123/b2898e011f954e2fa7cd26b9596ec60f.png