R绘图学习笔记

R软件作图学习，首先为了体验方便，我使用的R中MASS包中的自带数据集，首先加载该包

> library(MASS)

加载数据集，该数据集事保险数据统计

> data("Insurance")

> dim(Insurance)

查看数据的的行列元信息，发现是65行，5列

[1] 64  5

定义一个元信息的变量用于显示的需要

> var=c("District","Age")

> Insurance[20:25,var]

District   Age

20        2   >35

21        2   <25

22        2 25-29

23        2 30-35

24        2   >35

25        2   <25

统计数据的头字段，该字段的意义，Insurance数据集是记录了某保险公司1973年的第三季度的车险投保人数的相关信息，其中

District表示投保人家庭住址所在区域，取值1－4之间，

Group表示所投保汽车的发动机排量，分为小于1升，1－1.5升，1.5-2升，大于2升的四个等级

Age表示投保人的年龄：取值小于25，25-29，30-35，大于35岁

Holders表示投保人的数量

Claims表示索赔的投保人数

可以通过attributes() 函数来查看数据的属性列表，具体包括变量名称$name，数据集格式$class，以及行名称$row.names三个部分，由此组成了数据集中的一个整体的结构。

同时可以通过str()函数继续观察数据的内部结构，会发现数据的内部一些基本信息，同时还有summary函数进行查看。

> names(Insurance)

[1] "District" "Group"    "Age"      "Holders"  "Claims"

> head(Insurance, n=10)

District  Group   Age Holders Claims

1         1    <1l   <25     197     38

2         1    <1l 25-29     264     35

3         1    <1l 30-35     246     20

4         1    <1l   >35    1680    156

5         1 1-1.5l   <25     284     63

6         1 1-1.5l 25-29     536     84

7         1 1-1.5l 30-35     696     89

8         1 1-1.5l   >35    3582    400

9         1 1.5-2l   <25     133     19

10        1 1.5-2l 25-29     286     52

> class(Insurance$Age)

[1] "ordered" "factor"

> levels(Insurance$Age)

[1] "<25"   "25-29" "30-35" ">35"

画出Claims的直方图

> hist(Insurance$Claims,main = "Histogram of Freq of Insurance$Claims")

查看直方图的内部相信信息

> str(hist)

function (x, ...)

> str(hist(Insurance$Claims,breaks=20,labels = TRUE,col = "black",border = "white",main = "Histogram of Insurance$Claims whth 20 hars"))

List of 6

$ breaks  : num [1:21] 0 20 40 60 80 100 120 140 160 180 ...

$ counts  : int [1:20] 30 13 5 5 3 2 0 2 0 1 ...

$ density : num [1:20] 0.02344 0.01016 0.00391 0.00391 0.00234 ...

$ mids    : num [1:20] 10 30 50 70 90 110 130 150 170 190 ...

$ xname   : chr "Insurance$Claims"

$ equidist: logi TRUE

- attr(*, "class")= chr "histogram"

> str(hist(Insurance$Claims,breaks=20,labels = TRUE,col = "yellow",border = "white",main = "Histogram of Insurance$Claims whth 20 hars"))

List of 6

$ breaks  : num [1:21] 0 20 40 60 80 100 120 140 160 180 ...

$ counts  : int [1:20] 30 13 5 5 3 2 0 2 0 1 ...

$ density : num [1:20] 0.02344 0.01016 0.00391 0.00391 0.00234 ...

$ mids    : num [1:20] 10 30 50 70 90 110 130 150 170 190 ...

$ xname   : chr "Insurance$Claims"

$ equidist: logi TRUE

- attr(*, "class")= chr "histogram"

添加密度曲线图和直方图交汇

> hist(Insurance$Claims,freq=FALSE,density = 20,

+ main= "Histrogrm of Densitry of Insurance$Clamis")

> lines(density(Insurance$Claims))

> hist(Insurance$Claims,freq=FALSE,density = 20,

+ main= "Histrogrm of Densitry of Insurance$Clamis")

> lines(density(Insurance$Claims))

由于原始数据没有在Age变量的各个水平下Claims的分布情况，因此我们需要计算在四个age阶段Claims的值，程序如下，其中用到了names.arg是命名的形式表示，标注出条形图中各矩形所对应的离散数值水平

> Claims_Age = with(Insurance,c(

+ sum(Claims[which(Age=="<25")]),

+ sum(Claims[which(Age=="25-29")]),

+ sum(Claims[which(Age=="30-35")]),

+ sum(Claims[which(Age==">35")])))

> Claims_Age

[1]  229  404  453 2065

> barplot(Claims_Age,names.arg = c("<25","25-29","30-35",">35"),density = rep(20,4),main = "Distribution of age by Claims", xlab = "Age", ylab = "Claims")

> barplot(Claims_Age,names.arg = c("<25","25-29","30-35",">35"),density = rep(30,4),main = "Distribution of age by Claims", xlab = "Age", ylab = "Claims")

同理统计Holders与Age的对应关系

> Holders_Age = with(Insurance,c(sum(Holders[which(Age=="<25")]),

+ sum(Holders[which(Age=="25-29")]),

+ sum(Holders[which(Age=="30-35")]),

+ sum(Holders[which(Age==">35")])))

> data_bar=rbind(Claims_Age,Holders_Age)

> data_bar

[,1] [,2] [,3]  [,4]

Claims_Age   229  404  453  2065

Holders_Age 1138 2336 3007 16878

绘制连体直方图将Holders—Age，Claims－Age进行绑定

> barplot(data_bar,names.arg = c("<25","25-29","30-35",">35"),

+ beside=TRUE,

+ main="Age Distrbution by Claims and Holders",

+ xlab="Age",ylab="Claims&Holders",col=c("red","green"))

绘制内嵌直方图将Holders—Age，Claims－Age进行绑定

> legend(x="topleft",rownames(data_bar),fill = c("red","green"))

> barplot(data_bar,names.arg = c("<25","25-29","30-35",">35"),

+ beside=FALSE,

+ main="Age Distrbution by Claims and Holders",

+ xlab="Age",ylab="Claims&Holders",col=c("red","green"))

> legend(x="topleft",rownames(data_bar),fill = c("red","green"))

绘制点阵图

> dotchart(data_bar,xlab = "Claims&Holders",pch = 1:2,

+ col=c("red","green"),

+ main="Age Distribution by Claims and Holders")

绘制饼图

> pie(Claims_Age,labels = c("<25","25-29","30-35",">35"),

+ main="Pie Chart of Age by Claims",

+ col=c("green","red","yellow","blue"))

绘制带百分比的饼图

> percent=round(Claims_Age/sum(Claims_Age)*100)

> label=paste(paste(c("<25","25-29","30-35",">35"),":"),percent,"%",sep = "")

> pie(Claims_Age,labels = label,

+ main="pie chart of Age by Claims",col=c("blue","red","yellow","green"))

绘制3D饼图

> library(plotrix)

> pie3D(Claims_Age,labels = c("<25","25-29","30-35",">35"),explode = 0.05,

+ main="3D Pie Chart of Age by Claims",labelcex=0.8,

+ col=c("red","yellow","green","blue"))