R語言支持很多圖形，並且有些圖形是非常少見的，可能也因為自己不是專業弄數據分析的所以就孤陋寡聞了，總結下目前學習到的圖形。
條形圖
這個圖比較常見，很多數據統計軟件都支持這種圖形，這種圖形可以很好的展示數據的匯總結果，可以簡潔明了的方式表達數據背后的含義
> library(vcd) > counts<-table(Arthritis$Improved) > counts None Some Marked 42 14 28 > barplot(counts,main="Simple Bar Plot",xlab="Improvement",ylab=""Frequency) Error: unexpected symbol in "barplot(counts,main="Simple Bar Plot",xlab="Improvement",ylab=""Frequency" > barplot(counts,main="Simple Bar Plot",xlab="Improvement",ylab="Freqency") > > barplot(counts,main="Horizontal Bar Plot",xlab="Frequency",ylab="Improvement",horiz=TRUE)
堆砌圖
這個圖是條形圖的進化版本，它可以表達出更加豐富的含義，如果說條形圖只能表達兩個維度的結果，那么堆砌圖則能表達三個維度的數據分析結果
library(vcd)
> counts<-table(Arthritis$Improved,Arthritis$Treatment)
> counts
Placebo Treated
None 29 13
Some 7 7
Marked 7 21
> barplot(counts,main="Stacked Bar Plot",xlab="Treatment",ylab="Frequency",col=c("red","yellow","green"),legend=rownames(counts))
分組條形圖
和上面的堆砌圖一樣的效果，只是數據的展現方式不一樣。
> barplot(counts,main="Stacked Bar Plot",xlab="Treatment",ylab="Frequency",col=c("red","yellow","green"),legend=rownames(counts),beside=TRUE)
均值圖
個人覺得和條形圖類型，就圖形而言，沒有顯著的差別。
states<-data.frame(state.region,state.x77)
means<-aggregate(states$Illiteracy,by=list(state.region),FUN=mean)
> means
Group.1 x
1 Northeast 1.000000
2 South 1.737500
3 North Central 0.700000
4 West 1.023077
> means<-means[order(means$x),]
> means
Group.1 x
3 North Central 0.700000
1 Northeast 1.000000
4 West 1.023077
2 South 1.737500
> barplot(means$x,names.arg = means$Group.1)
> title("Mean Illiteracy Rate")
>
>
> par(mar=c(5,8,4,2))
> par(las=2)
> counts<-table(Arthritis$Improved)
> barplot(counts,main="Treatment Outcome", horiz=TRUE, cex.name=0.8, names.arg = c("No Improvement","Some Improvement", "Marked Improvement"))
>
荊狀圖
和堆砌圖類似，但是所有分組的高度都是一樣的，唯一不同的則是分組中的色塊面積大小，用來分析數據在某種情況下所占比例比較合適。
> library(vcd) > counts<-table(Treatment,Improved) Error in table(Treatment, Improved) : object 'Treatment' not found > attach(Arthritis) > counts<-table(Treatment,Improved) > spine(counts,main="Spinogram Example") > counts Improved Treatment None Some Marked Placebo 29 7 7 Treated 13 7 21
餅圖
最常見的圖，不多說了
library(plotrix)
> 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)
> lbls2<-paste(lbls," ",pct,"%",sep="")
> lbls2
[1] "US 20%" "UK 24%" "Australia 8%" "Germany 32%" "France 16%"
> pie(slices,labels=lbls,explode=0.1,main="3D Pie Chart ")
> pie(slices,labels=lbls2,col=rainbow(length(lbls2)),main="Pie Chart wit Precentage")
> pie3D(slices,labels=lbls,explode=0.1,main="3D Pie Chart ")
> mytable<-table(state.region)
> pie(mytable,labels=lbls3,main="Pie Chart from a Table\n (with sample sizes)")
扇形圖
和餅圖類型，不過這個圖形還是比較少見的
> library(plotrix)
> slices<-c(10,12,4,16,8)
> lbls<-c("US","UK","Australia","Germany","France")
> fan.plot(slices,labels=lbls,main="Fan Plot")
直方圖
柱圖，最常見的圖，和之前提到的條形圖類似。
> par(mfrow=c(2,2)) > hist(mtcars$mpg) > > hist(mtcars$mpg,breaks=12,col="red",xlab="Miles Per Gallon",main="Colored histogram with 12 bins") > > > hist(mtcars$mpg,freq=FALSE,col="red",xlab="Miles Per Gallon",main="Histogram, rug plot, density curve") > rug(jitter(mycars$mpg)) #軸須圖 > lines(density(mtcars$mpg),col="blue",lwd=2) #密度曲線 > x<-mtcars$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$mids[1:2])*length(x) > lines(xfit,yfit,col="blue",lwd=2) > box() > mtcars$mpg [1] 21.0 21.0 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 17.8 16.4 17.3 15.2 10.4 10.4 [17] 14.7 32.4 30.4 33.9 21.5 15.5 15.2 13.3 19.2 27.3 26.0 30.4 15.8 19.7 15.0 21.4
核密度圖
這個圖形比較少見，有點像原始版本的熱點圖，用來顯示變量的密度關系。
> library(sm)
>par(mfrow=c(2,1))
> d<-density(mtcars$mpg)
> plot(d)
> d<-density(mtcars$mpg)
> plot(d,main="Kernel Density of Miles Per Gallon")
> polygon(d,col="red",border="blue")
> 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)))) #這行代碼沒效果
> legend(locator(1),levels(cyl.f),fill=colfill)
箱線圖
這個圖也比較有意思，它主要關注一組觀察變量的5個指標：Min，1/4，mean，4/3，Max。第一次發現這么有意思的分析方式，不過在日常的統計中，這5ge指標應該是經常被使用的，所以箱線圖也是非常實用的一種圖形。
boxplot(mtcars$mpg,main="Box plot",ylab="Miles per Gallon")
>
> boxplot(mpg~cyl,data=mtcars,main="Car Mileage Data", xlab="Number of Cylinders",ylab="Miles Per Gallon")
boxplot(mpg~cyl,data=mtcars,notch=TRUE,varwidth=TRUE,col="red",main="Car Mileage Data",xlab="Number of Cylinders",ylab="Miles Per Gallon") #有對稱效果的箱線圖，該圖形包含了變量密度信息
#分組箱線圖
mtcars$cyl.f<-factor(mtcars$cyl,levels=c(4,6,8),labels=c("4","6","8"))
> mtcars$cyl.f
mtcars$am.f<-factor(mtcars$am,levels=c(0,1),labels=c("auto","standard"))
> mtcars$am.f
[1] standard standard standard auto auto auto auto auto auto
[10] auto auto auto auto auto auto auto auto standard
[19] standard standard auto auto auto auto auto standard standard
[28] standard standard standard standard standard
Levels: auto standard
> boxplot(mpg~am.f*cyl.f,data=mtcars,varwidth=TRUE,col=c("gold","darkgreen"),main="MPG Distribution by Auto Type",xlab="Auto Type",ylab="Miles Per Gallon")
>
小提琴圖
和箱線圖的分析套路類似，但是提供更加明確的變量密度分布信息。
> library(vioplot)
x1<-mtcars$mpg[mtcars$cyl==4]
> x2<-mtcars$mpg[mtcars$cyl==6]
> x3<-mtcars$mpg[mtcars$cyl==8]
> vioplot(x1,x2,x3,names=c("4 cyl","6 cyl","8 cyl"),col="gold")
> title("Violin Plots of Miles Per Gallon",ylab="Miles Per Gallon",xlab="Number of Cylinders")
點圖
也是一種比較常見的圖，它的進化版本應該是散點圖
> dotchart(mtcars$mpg, labels=row.names(mtcars),cex=.7,main="Gas Mileage for Car Models",xlab="Miles Per Gallon") > #分組散點圖 > x<-mtcars[order(mtcars$mpg),] > x$cyl<-factor(x$cyl) > x$color[x$cyl==4] <- "red" > x$color[x$cyl==6] <- "blue" > x$color[x$cyl==8]<- "darkgreen" > dotchart(x$mpg,labels=row.names(x),cex=.7,groups=x$cyl,gcolor="black",color=x$color,pch=19,main="Gas Mileage for Car Models\ngrouped by cylinder", xlab="Miles Per Gallon")