R语言实战-读书笔记 （第6章 基础图形）

***********************************

与导图结合的脚本文件：
创建脚本：文件——新建脚本程序，将以下代码复制粘贴至脚本内，选中右键运行当前或所选代码。

#第6章 基础图形#

install.packages("vcd")#载入包，使用包中的Arthritis数据#
library(vcd)
counts <- table(Arthritis$Improved)#提取各单元的计数#
counts
barplot(counts,main="Simple Bar Plot",
xlab="Improvement", ylab="Frequency")#简单条形图#
barplot(counts,main="Horizontal Bar Plot",
xlab="Frequency", ylab="Improvement",
horiz=TRUE)#水平条形图#

plot(Arthritis$Improved, main="Simple Bar Plot",
xlab="Improved", ylab="Frequency")
plot(Arthritis$Improved, horiz=TRUE, main="Horizontal Bar Plot",
xlab="Frequency", ylab="Improved")

#堆砌和分组条形图#
counts <- table(Arthritis$Improved, Arthritis$Treatment)
counts
barplot(counts,main="Stacked Bar Plot",
xlab="Treatment", ylab="Frequency",
col=c("red", "yellow","green"),
legend=rownames(counts))#堆砌#
barplot(counts,
main="Grouped Bar Plot",
xlab="Treatment", ylab="Frequency",
col=c("red", "yellow", "green"),
legend=rownames(counts), beside=TRUE)#条形#

#均值条形图#
states <- data.frame(state.region, state.x77)
head(states)
means <- aggregate(states$Illiteracy, by=list(state.region), FUN=mean)
means
means <- means[order(means$x),]#升序排序#
barplot(means$x, names.arg=means$Group.1)#means是一个数据框，不是向量和矩阵#
#means$x 是包含各条形高度的向量，而添加选项 names.arg=means$Group.1是为了展示标签。#
title("Mean Illiteracy Rate")

#条形图微调#
par(mar=c(5,8,4,2))#增加y边界大小“8”#
par(las=2)#旋转条形的标签，看X轴#
counts <- table(Arthritis$Improved)
barplot(counts,
main="Treatment Outcome",
horiz=TRUE,
cex.names=0.8,#缩小字体大小，标签Y轴#
names.arg=c("No Improvement", "Some Improvement","Marked Improvement"))

#棘状图 #
library(vcd)
attach(Arthritis)
counts <- table(Treatment, Improved)
counts
spine(counts, main="Spinogram Example",margins = c(5.1, 4.1, 4.1, 3.1))
detach(Arthritis)

#饼图#
par(mfrow=c(2, 2))
slices <- c(10, 12,4, 16, 8)
lbls <- c("US", "UK", "Australia", "Germany", "France")
pie(slices, labels = lbls,main="Simple Pie Chart")
pct <- round(slices/sum(slices)*100)
pct
lbls2 <- paste(lbls, " ", pct, "%", sep="")
#paste(c('A','B','C','D','E'),c(1,2),sep = '-') sep为连接形式#
lbls2
pie(slices, labels=lbls2, col=rainbow(length(lbls2)),
main="Pie Chart with Percentages")
mytable <- table(state.region)
lbls3 <- paste(names(mytable), "\n", mytable, sep="")
pie(mytable, labels = lbls3,
main="Pie Chart from a Table\n (with sample sizes)")
margins = c(5.1, 4.1, 6.1, 3.1)
#扇形图#
install.packages("plottrix")
library(plotrix)
slices <- c(10, 12,4, 16, 8)
lbls <- c("US", "UK", "Australia", "Germany", "France")
fan.plot(slices, labels = lbls, main="Fan Plot")

#直方图#
par(mfrow=c(2,2))
hist(mtcars$mpg)#简单直方图#
hist(mtcars$mpg,breaks=12,col="red",
xlab="Miles Per Gallon",main="Colored histogram with 12 bins")#指定数组和颜色#
hist(mtcars$mpg,freq=FALSE,breaks=12,col="red",
xlab="Miles Per Gallon",main="Histogram, rug plot, density curve")
rug(jitter(mtcars$mpg))#添加轴虚图#
lines(density(mtcars$mpg), col="blue", lwd=2)#添加密度曲线#
x <- mtcars$mpg
h<-hist(x,breaks=12,col="red",
xlab="Miles Per Gallon",main="Histogram with normal curve and box")
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)#添加正态分布曲线#
lines(xfit, yfit, col="blue", lwd=2)
box()

#核密度图#
par(mfrow=c(2,1))
d <- density(mtcars$mpg)
plot(d)
plot(d, main="Kernel Density of Miles Per Gallon")
polygon(d, col="red", border="blue")
rug(mtcars$mpg, col="brown")
install.packages("sm")

library(sm)
par(mfrow=c(1,1))
attach(mtcars)
cyl.f <- factor(cyl, levels= c(4,6,8),
labels = c("4 cylinder", "6 cylinder",
"8 cylinder"))
sm.density.compare(mpg, cyl, xlab="Miles Per Gallon")
title(main="MPG Distribution by Car Cylinders")
colfill<-c(2:(1+length(levels(cyl.f))))
legend(locator(1), levels(cyl.f),fill=colfill)
detach(mtcars)

#箱线图#
boxplot(mtcars$mpg, main="Box plot", ylab="Miles per Gallon")
boxplot.stats(mtcars$mpg) 

boxplot(mpg ~ cyl, data=mtcars,
main="Car Mileage Data",
xlab="Number of Cylinders",
ylab="Miles Per Gallon")

boxplot(mpg ~ cyl, data=mtcars,
notch=TRUE,
varwidth=TRUE,
col="red",
main="Car Mileage Data",
xlab="Number of Cylinders",
ylab="Miles Per Gallon")

mtcars$cyl.f <- factor(mtcars$cyl,
levels=c(4,6,8),
labels=c("4","6","8"))
mtcars$am.f <- factor(mtcars$am,
levels=c(0,1),
labels=c("auto", "standard"))
boxplot(mpg ~ am.f *cyl.f,
data=mtcars,
varwidth=TRUE,
col=c("gold","darkgreen"),
main="MPG Distribution by Auto Type",
xlab="Auto Type", ylab="Miles Per Gallon")

#小提琴图#
install.packages("vioplot")
library(vioplot)
x1 <- mtcars$mpg[mtcars$cyl==4]
x2 <- mtcars$mpg[mtcars$cyl==6]
x3 <- mtcars$mpg[mtcars$cyl==8]
vioplot(x1, x2, x3,
names=c("4 cyl", "6 cyl", "8 cyl"),
col="gold")
title("Violin Plots of Miles Per Gallon", ylab="Miles Per Gallon",
xlab="Number of Cylinders")

#点图#
head(mtcars)
dotchart(mtcars$mpg, labels=row.names(mtcars), cex=.7,
main="Gas Mileage for Car Models",
xlab="Miles Per Gallon")

x <- mtcars[order(mtcars$mpg),]#根据每加仑汽油行驶英里数（从最低到最高）对数据框 mtcars 进行排序，结果保存为数据框 x#
head(x)
x$cyl <- factor(x$cyl)#将数值向量 cyl 转换为一个因子#
x$color[x$cyl==4] <- "red"
x$color[x$cyl==6] <- "blue"
x$color[x$cyl==8] <- "darkgreen" #添加一个字符型向量 （ color ）到数据框 x 中，根据 cyl 的值，它所含的值为 "red" 、 "blue" 或 "darkgreen"#
head(x)
dotchart(x$mpg,
labels = row.names(x),
cex=.7,
groups = x$cyl,
gcolor = "black",#数字4、6和8以黑色显示#
color = x$color,#点和标签的颜色来自向量 color#
pch=19,
main = "Gas Mileage for Car Models\ngrouped by cylinder",
xlab = "Miles Per Gallon")