R语言数据可视化部分

数据挖掘

R语言数据可视化部分

散点图

library(datasets)

head(cars)

plot(cars)

plot(cars$dist,cars$speed,xlab = "dist", ylab = "speed",xlim = c(0,20))

attach(cars)

plot(dist,speed,xlab = "dist",ylab = "speed")

plot(cars$dist,cars$speed,xlab = "dist",ylab = "speed",main = "cars 散点图",type="b",pch=4,lwd=2,col="red")

a<-c(20,30,40,50,60)

b<-c(11,22,33,44,66)

c<-c(15,25,35,45,55)

plot(a,b,type = "b")#有点，用线连接

plot(a,b,type = "o")#有点，线连接，线过点

plot(a,b,type = "p")#点图

plot(a,b,type = "h")#用线表示值

plot(a,b,type = "l")#直接线链接

plot(a,b,type = "s")#梯形图

plot(a,b,type = "S")#梯形图

plot(a,b,type = "n")#不做图

plot(a,b,pch=0)

plot(a,b,pch=1)

plot(a,b,pch=2)

plot(a,b,pch=3)

plot(a,b,lty=2,lwd=2,pch=15,cex=2)

plot(a,b,type="b",lty=2,lwd=2,pch=15,cex=2)

install.packages("RColorBrewer")

library(RColorBrewer)

plot(a,b,type="b",lty=2,lwd=2,pch=15,cex=2,col=2)

opar<-par(no.readonly = FALSE)

par(pin=c(2,3))

par(lwd=2,cex=1.5)

par(cex.axis=.75,font.axis=3)

plot(a,b,type="b",pch=19,lty=2,col=2)

plot(a,b,type="b",pch=23,lty=5,col=2,bg="green")

par(opar)

par(mfrow = c(2, 2))

plot(a,c,type = "o",col=3,lty=3,pch=3,lwd=4,

main = "实验图形",xlab="a",ylab="c",

xlim = c(0,100),ylim=c(0,100))

x<-c(1:15)

y<-x

z<-10/x

opar<-par(no.readonly = TRUE)

par(mar=c(5,4,4,8)+0.1)

plot(x,y,type = "b",pch=21,col=2,yaxt="n",lty=3,ann = FALSE)

lines(x,z,type = "b",pch=3,col=4,lty=2)

axis(side = 2,at=x,labels = x,col.axis=2,las=2)

axis(side = 4,at=z,labels = round(z,digits = 2),

cex.axis=2,las=2)

par(opar)

library(datasets)#加载数据包

attenu#

attach(attenu)

subset(attenu,dist>=40)#选出dist列大于等于14的一行

df<-subset(attenu,event=="2" & dist=="107",select=c(dist));df#显示特定的行

s=subset(attenu,event=="2" & dist=="107",select=c(event,dist));s#多条件查询

df1<-as.list(attenu);df1#转换成列表

append(df1$event,123)#在event后部分追加123这个数

append(df1,1235,after = 55)#指定长度追加

data1= data.frame(Id=c(1:6),Product=c(rep("Toaster",3),rep("Radio",3)))

data2 = data.frame(Id=c(2,4,6,7),State=c(rep("Alabama",3),rep("Ohio",1)))

merge(data1,data2,all=T)#取两数据框并集

merge(data1,data2,all = F)#取交集

merge(data1,data2,all=FALSE)#只是列先后的区别

merge(data1, data2, all.x=TRUE)#以df1所拥有的显示

merge(data1,data2)

#有两个及以上相同的列，合并则会自动选择两个均相同的，

#结果同merge(df1, df2, by = c("id", "sex"))

merge(data1,data2,by="Id")#两数据框中共有的sex那一列则会以sex.x和sex.y形式输出。

#aggregate()函数

mtcars#R语言自带的汽车数据集

attach(mtcars)

str(mtcars)#查看数据集的列名

aggregate(mtcars,by=list(cyl,gear),FUN = mean)#使用aggregate函数按cyl（汽缸数）进行分类计算平均值

#公式是一种特殊的R数据对象，在aggregate函数中使用公式参数可以对数据框的部分指标进行统计

aggregate(cbind(mpg,hp) ~ cyl+gear, FUN=mean)

#频次统计table

table(hp)#统计mtcars数据中的hp列中出现结果频次

#函数apply(),list,matrix,array三种形式均可以

rname = c("r1","r2","r3")

cname = c("c1","c2")

b<-matrix(1:6,nrow=3, dimnames = list(rname, cname))

apply(b,1,sum)#1—表示按行计算，2—按列计算；

apply(b,2,sum)#1—表示按行计算，2—按列计算；

m<-c("SPYDERMAN","BATMAN","VERTIGO","CHINATOWN")

m1<-lapply(m,tolower)#把大写的字符改成小写

sapply(mtcars,min)#查找数据框中最小的

tapply(mtcars$mpg, INDEX=mtcars$mpg, FUN = mean)#计算数据框中的列或者向量里的均值

条形图

#条形图 install.packages("vcd") install.packages("plottrix") install.packages("sm") install.packages("vioplot") library(vcd) a<-table(Arthritis$Treatment);a hist(a) barplot(a,main = "条形图",ylab="Frequency", xlab="Treatment",ylim=c(0,50))#条形图绘制 barplot(a,main = "条形图",ylab="Treatment", xlab="Frequency",xlim=c(0,50),horiz=TRUE)#条形图绘制 plot(Arthritis$Improved,main = "条形图",xlab="Improved", ylab="Frequency")
counts <- table(Arthritis$Improved, Arthritis$Treatment) counts #堆切 barplot(counts, main = "条形图", xlab = "Treatment", ylab = "Frequency", col = c("red", "yellow", "green"), legend = rownames(counts))
#分组 barplot(counts, main = "条形图", xlab = "Treatment", ylab = "Frequency", col = c("red", "yellow", "green"), legend = rownames(counts), beside = TRUE)
#均值条形图 states <- data.frame(state.region, state.x77) means <- aggregate(states$Illiteracy, by = list(state.region), FUN = mean)#以列表的形式计算均值 means means <- means[order(means$x), ]#排序 means barplot(means$x, names.arg = means$Group.1)#把均值做条形图 title("Mean Illiteracy Rate")
#调条形图 par(mar = c(5, 8, 4, 2))#增加Y的边界 par(las = 2)#旋转条形图的标签 counts <- table(Arthritis$Improved) barplot(counts, main = "Treatment Outcome", horiz = TRUE, cex.names = 0.8, names.arg = c("No Improvement", "Some Improvement", "Marked Improvement"))
#棘状图用spine()，看比例 attach(Arthritis) counts <-table(Treatment, Improved) spine(counts, main = "棘状图") detach(Arthritis)

饼图

#饼图

par(mfrow = c(2, 2))

s<- c(10, 12, 4, 16, 8)

lbls <- c("A", "B", "C", "D", "E")

pie(s,labels = lbls, main = "饼图")

pct <- round(s/sum(s) * 100)#求百分比

lbls2 <- paste(lbls, " ", pct, "%", sep = "")

pie(s, labels = lbls2, col = rainbow(length(lbls)),

main = "饼图")

install.packages("plotrix")

library(plotrix)

pie3D(s, labels = lbls, explode = 0.1, main = "3D 饼图 ")

mydata<-table(state.region)

lbls <-paste(names(mydata), " ", mydata, sep = "")

pie3D(mydata, labels = lbls, main = "饼图1")

#扇形图

slices<-c(10, 12, 4, 16, 8)

lbls<-c("US", "UK", "Australia", "Germany", "France")

fan.plot(slices, labels = lbls, main = "扇形图")

散点图

#散点图

attach(mtcars)

par(mfrow=c(2,2))

plot(wt, mpg,

main="Basic Scatterplot of MPG vs. Weight",

xlab="Car Weight (lbs/1000)",

ylab="Miles Per Gallon ", pch=19)

abline(lm(mpg ~ wt), col="red", lwd=2, lty=1)

lines(lowess(wt, mpg), col="blue", lwd=2, lty=2)

#loess(),lowess()

library(car)

scatterplot(mpg ~ wt | cyl, at=cyl,data=mtcars, lwd=2,

main="Scatter Plot of MPG vs. Weight by Cylinders",

xlab="Weight of Car (lbs/1000)",

ylab="Miles Per Gallon", id.method="identify",

legend.plot=TRUE, labels=row.names(mtcars),

boxplots="xy")

#散点图矩阵

attach(mtcars)

pairs(~mpg+disp+wt+drat,data=mtcars,main="汽车数据矩阵散点图")

library(car)

scatterplotMatrix(~mpg+disp+drat+wt,data=mtcars,spread=FALSE,

smoother.args=list(lty=2),

main="散点图矩阵")

#spread=FALSE;选项表示不添加展示分散度和对称信息的直线

#smoother.args=list(lty=2);设定loess()拟合曲线是用虚线而不是实线

scatterplotMatrix(~mpg+disp+drat+wt,data=mtcars,spread=TRUE,

smoother.args=list(lty=1),

main="散点图矩阵")

#不同风格

install.packages("glus")

library(glus)

install.packages("TeachingDemos")

library(TeachingDemos)

pairs2()

install.packages("HH")

installed.packages("ResourceSelection")

#高密度散点图

set.seed(1234)

n <- 10000

c1 <- matrix(rnorm(n, mean=0, sd=0.5), ncol=2)

c2 <- matrix(rnorm(n, mean=3, sd=2), ncol=2)

mydata <- rbind(c1, c2)

mydata <- as.data.frame(mydata)

names(mydata) <- c("x", "y")

with(mydata,

plot(x, y, pch=19, main="高密度散点图"))

with(mydata,

smoothScatter(x, y, main="高密度散点图"))

library(hexbin)

with(mydata, {

bin <- hexbin(x, y, xbins=50)

plot(bin, main="Hexagonal Binning with 10,000 Observations")

})

library(IDPmisc)#做的散点图对大数据集的创建可读性比较好

with(mydata,

iplot(x, y, main="Image Scatter Plot with Color Indicating Density"))

par(opar)

#多维可视化散点图

install.packages("scatterplot3d")

library(scatterplot3d)

attach(mtcars)

scatterplot3d(wt,disp,mpg,main = "3d 散点图")

scatterplot3d(wt, disp, mpg,

pch=16,

highlight.3d=TRUE,

type="h",

main="3D 散点图")

#highlight.3d=TRUE；填充颜色

s3d <-scatterplot3d(wt, disp, mpg,

pch=16,

highlight.3d=TRUE,

type="h",

main="3D 散点图")

fit <- lm(mpg ~ wt+disp)

s3d$plane3d(fit)

detach(mtcars)

#3d旋转散点图1

install.packages("rgl")

library(rgl)

attach(mtcars)

plot3d(wt,disp,mpg,col="blue",size=5)

折线图

#展示五种树的生长情况

Orange$Tree<- as.numeric(Orange$Tree)#转换成数值型

ntrees <-max(Orange$Tree);ntrees

#创建图形

#range返回一个包含所有给定参数的最小值和最大值的向量。

xrange <- range(Orange$age);xrange

yrange <- range(Orange$circumference);yrange

plot(xrange, yrange,

type="n",

xlab="Age (days)",

ylab="Circumference (mm)")

#rainbow创建一个由n个相邻颜色组成的向量。

colors <-rainbow(ntrees)

linetype <- c(1:ntrees)#绘制1：5的颜色

plotchar <-seq(18,18+ntrees,1);plotchar#绘图的类型

#绘制图形

for (i in 1:ntrees) {

tree<-subset(Orange,Tree==i)

lines(tree$age,tree$circumference,

type="b",

lwd=2,

lty=linetype[i],

col=colors[i],

pch=plotchar[i]

)

}

#lty=linetype[i], 1-5的绘图风格

#col=colors[i],颜色从1-5的编号

#pch=plotchar[i]，18-23 的绘制符号

title("树子的生长折线图", "绘图例子")

#添加标签legend

legend(xrange[1], yrange[2],

1:ntrees,

cex=0.8,

col=colors,

pch=plotchar,

lty=linetype,

title="Tree"

)

# cex=0.8图形缩放0.8倍

不同包作图比较

#不同的程序包作图比较

data<-read.csv("J:shuju/Facet_Data.csv",sep = ",",header = T)

str(data)

attach(data)

#graphics包作图

library(ggplot2)

plot(SOD,tau,main = "实验散点图")#散点图

hist(SOD,breaks=30,ylim=c(0,40),main = "")

boxplot(SOD~Class,data = data,xlab = "Class",ylab = "SOD")

#lattice包作图

library(lattice)

xyplot(SOD~tau,col="black",main="实验散点图")

histogram(~SOD,data,type="count",nint=30,col="white")

bwplot(SOD~Class,data,xlab = "Class",par.settings=canonical.theme(color = FALSE))

#ggplot2包作图

library(graphics)

ggplot(data,aes(x=SOD,y=tau))+geom_point(shape=21,main="实验散点图")

ggplot(data,aes(SOD))+geom_histogram(bins=30,colour="black",fill="white")

ggplot(data,aes(x=Class,y=SOD))+geom_boxplot()

核密度函数图

#密度图

mtcars

attach(mtcars)

par(mfrow = c(2, 1))

d<-density(mpg)

plot(d)

d<-density(mpg)

plot(d, main = "Kernel Density of Miles Per Gallon")

polygon(d, col = "red", border = "blue")#填充

rug(mpg, col = "brown")

#多组密度图

library(sm)

a<-factor(cyl,levels = c(4,6,8),

labels = c("4A","6A","8A"))

sm.density.compare(mpg,cyl,xlab="hfhhj")

title(main = "hyhbhkajbkjhu")

c<-c(2:(1+length(levels(a))))

length(locator(1),levels(a),fill=colfill)

马瑟克图

#马赛克图
###############################################################
#逻辑指定是否应该使用gp(参见gp)。如果TRUE和expected未指定， #
#;则会拟合一个默认模型:如果指定了condvars(请参见strucplot)， #
#则会拟合一个相应的条件独立模型，否则将拟合一个完全独立模型 #
###############################################################
ftable(Titanic)#创建“ 泰坦尼克数据”列联表。
library(vcd)
library(grid)
mosaic(Titanic, shade=TRUE, legend=TRUE)

箱线图

#箱线图
attach(mtcars)
boxplot(mpg,main="箱线图",ylab="gh")
#两个组之间的比较箱线图
boxplot(mpg~cyl,data=mtcars,main="jjgjh",
xlab = "hjklk",ylab = "ghjgkh")
#两个组之间的比较箱线图
boxplot(mpg ~ cyl, data = mtcars, notch = TRUE,
varwidth = TRUE, col = "red",
main = "Car Mileage Data",
xlab = "Number of Cylinders",
ylab = "Miles Per Gallon")
#两个交叉因子的箱线图
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",notch = TRUE)