[读书笔记] R语言实战 （六） 基本图形方法

1.  条形图 barplot()

#载入vcd包
library(vcd)
#table函数提取各个维度计数
counts <- table(Arthritis$Improved)
counts
#绘制简单Improved条形图
#1行2列
par(mfrow=c(1,2))
barplot(counts, main = "simple Bar plot", xlab = "Improved",ylab = "Frequency")
#绘制水平条形图 horiz = TRUE
barplot(counts,main = "simple Bar plot", xlab = "Frequency",ylab = "Improved",horiz=TRUE)
#如果绘制的是一个有序因子，可以使用plot()函数快速创建一幅垂直条形图
#1行1列
par(mfrow=c(1,1))
plot(Arthritis$Improved,xlab = "Frequency",ylab = "Improved",horiz=TRUE)
#如果要绘制的变量是一个矩阵而不是一个向量，将会绘制堆砌条形图或者分组条形图
#生成Improved和Treatment列联表
counts <- table(Arthritis$Improved,Arthritis$Treatment)
counts
#绘制堆砌图
barplot(counts,main = "Stacked Bar plot",xlab = "Treatment",ylab = "Frequency",col = c('red','yellow','green'),legend = rownames(counts))
#绘制分组条形图
barplot(counts,main = "Grouped Bar plot",xlab = "Treatment",ylab = "Frequency",col = c('red','yellow','green'),legend = rownames(counts),beside = TRUE)
#条形图微调
#增加y边界大小
par(mar = c(5,8,4,2))
#las=2旋转条形标签
par(las = 2)
counts <- table(Arthritis$Improved)
#cex.names= 0.8缩小字体的大小
barplot(counts,main="Treatment Outcomes",horiz = TRUE,cex.names=0.8,names.arg = c("No Improvement","Some Improvement","Marked Imporvement"))

2. 饼图：饼图在商业世界中无所不在，然而多数统计学家，包括R相应文档的编写者，都对它持否定态度。相对于饼图，他们更推荐使用条形图或点图，因为相对于

面积，人们对长度的判断更为精确 pie() pie3D()

par(mfrow=c(2,2))
slices <- c(10,12,12.4,16,8)
lbls <- c("US","UK","Austrialia","Germany","France")
pie(slices,labels=lbls,main="simple Chart")
pct <- round(slices/sum(slices)*100)
#拼接字符串和比例数值
lbls2 <- paste(lbls," ", pct,"%",sep = "")
lbls2
pie(slices,labels=lbls2,col=rainbow(length(lbls2)),main="Pie chart with percentage")
#载入ploirix包
library(plotrix)
#画简单3D图
pie3D(slices,labels=lbls,explode = 0.4,main = "3D pei chart")
#从表格创建饼图
#table取得region的计数表
mytable <- table(state.region)
#names 函数取得列名，然后将列名和相应的计数拼接在一起
lbls3 <- paste(names(mytable),'\n',mytable,sep="")
pie(mytable,labels=lbls3,main="pie chart from a table\n{with sample sizes}")

3. 直方图 ：可以展示连续变量的分布. hist(x,breaks=, freq = )

x是一个由数据值组成的数值向量，参数freq = FALSE表示根据概率密度而不是频数绘制图形，参数breaks用于控制数组的数量.

par(mfrow = c(2,2))
#简单直方图
hist(mtcars$mpg)
#指定组数和颜色
hist(mtcars$mpg,breaks=12,col='red',xlab="Miles Per Gallon",main="Colored histogram with 12 bins")
hist(mtcars$mpg,freq=FALSE,breaks=12,col='red',xlab="Miles Per Gallon",main="Histogram,rug plot, density curve")
rug(jitter(mtcars$mpg))
#添加核密度图
lines(density(mtcars$mpg),col='blue',lwd=2)
x <- mtcars$mpg
h <- hist(x,breaks=12,col='red',xlab="Miles Per Gallon",main="Histogram with normal curve and box")
#设置横轴范围和分度
xfit <- seq(min(x),max(x),length=40)
yfit <- dnorm(xfit,mean=mean(x),sd=sd(x))
yfit <-yfit*diff(h$mids[1:2]*length(x))
lines(xfit,yfit,col='blue',lwd=2)
box()

4. 核密度图：核密度估计是用于估计随机变量概率密度函数的非参数方法

#当前图像参数列表
opar <- par(no.readonly = TRUE)
par(mfrow=c(2,1))
#默认条件创建
d <- density(mtcars$mpg)
plot(d)
d <- density(mtcars$mpg)
#添加标题和曲线
plot(d,main="kernel Density of Miles per Gallon")
polygon(d,col='red',border="blue")
#添加棕色轴须图
rug(mtcars$mpg,col="brown")
#可比较的核密度函数
#线宽为双倍
#还原初始设置
par(opar)
par(lwd=2)
library(sm)
attach(mtcars)
sm.density.compare(mpg,cyl,xlab='Miles per gallon')
cyl.f <- factor(cyl,levels=c(4,6,8),labels=c("4 cylinder","6 cylinder","8 cylinder"))
title(main="MPG Distribution by Car Cylinders")
#创建颜色向量
colfill <- c(2:(1+length(levels(cyl.f))))
legend(locator(1),levels(cyl.f),fill=colfill)
detach(mtcars)

5. 箱线图：boxplot()

boxplot(mtcars$mpg,main="Box plot",ylab="Miles per gallon")
#并列箱线图跨列比较
boxplot(mpg~cyl,data=mtcars,main="Car Mileage Data",xlab="Number of Cylinders",ylab="Miles per gallon")
#图中可以看到四缸，六缸，八缸耗油中位数不同

6. 点图：在简单水平刻度上绘制大量有标签值的方法, dotchart()

dotchart(mtcars$mpg,labels=row.names(mtcars),cex=.7,main="Gas Mileage for Car Models",xlab="Miles Per Gallon")
#点图通常在经过排序并且分组变量被不同符号和颜色区分开最有用
x <- mtcars[order(mtcars$mpg),]
#分组变量转化为因子
x$cyl <-factor(x$cyl)
x$color[x$cyl==4]<-'red'
x$color[x$cyl==6]<-'blue'
x$color[x$cyl==8]<-'dark green'
dotchart(x$mpg,labels=row.names(x),cex=.7,group=x$cyl,gcolor="black",color=x$color,pch=19,
         main="Gas Mileage for Car models\n grouped by cylinder",xlab='Miles Per gallon')