ch11 Intermediate graphs
Sitong
2017年11月26日
本章主要讲解中级绘图函数，主要包括：
- 散点图
- plot
- scatterplot
- 散点图矩阵
- pairs
- scatterplotMatrix
- 添加线性和平滑曲线
- 主对角线放置箱线图，密度图，直方图
- 对边界添加轴须图
- smoothScatter利用光平滑密度估计绘制散点图
- 三维散点图
- satterplot3d绘制三维散点图
- 添加回归平面
- plot3d绘制旋转的散点图
- 气泡图
- symbols绘制气泡图
- 其他绘图
- plot-折线图
- corrgram-相关图
- order,panel,col参数的含义
- mosaic-马赛克图
1.散点图
下图为添加了最佳拟合曲线的散点图
attach(mtcars)
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)
detach(mtcars)注意上图中使用了lowess函数来平滑曲线loess函数拥有同样功能，具体平滑计算参见Cleveland 1981 car包中的scatterplot函数增强了对应功能：
# Scatter plot with fit lines by group
library(car)
scatterplot(mpg ~ wt | 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),
legend.coords="topright",
boxplots="xy")
library(car)
scatterplotMatrix(~mpg+disp+drat+wt,data = mtcars,
spread=FALSE,smoother.arg=list(lty=2),
main="Scatter Plot Matrix via car Package")
# spread设置是否添加分散度和对称信息曲线
# smooother设置平滑曲线类型用于绘制散点图矩阵的库及函数：
- glus-cpars()
- TeachingDemos-pairs2()
- ResourceSelection-kepairs()
- SMPracticals-pairs.mod()
2.散点图矩阵
当点数较多较密集时可以使用高密度散点图模式来绘制散点图：
set.seed(1234)
n=10000
c1=matrix(rnorm(n,mean = 0,sd = .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 = "Scatter Plot with 1000 Observations"))
高密度散点图的变形模式：
- smootherScatter()添加颜色透明度来代表点分布
- 添加hexbin()将二元变量的封箱放到六边形单元格中
with(mydata,
smoothScatter(x,y,main="Scatter Plot Colored by Smoothed Densities"))
library(hexbin)
with(mydata,{
bin=hexbin(x,y,xbins = 50)
plot(bin,main="Hexagonal Binning with 10,000 Observations")
})
3.三维散点图
同时我们可以将散点图应用于三维的数据格式，如下：
library(scatterplot3d)
attach(mtcars)
scatterplot3d(wt,disp,mpg,
main = "Basic 3D Scatter Plot")
scatterplot3d(wt,disp,mpg,
pch=16,
highlight.3d = TRUE,
type = "h",
main = "3D Scatter Plot with Vertical Lines and Regression Plane")
s3d <-scatterplot3d(wt, disp, mpg,
pch=16,
highlight.3d=TRUE,
type="h",
main="3D Scatter Plot with Vertical Lines and Regression Plane")
fit=lm(mpg~wt+disp)
s3d$plane3d(fit)
detach(mtcars)当需要添加旋转观察模式时，我们可以选用如下两种函数进行交互：
- rgl::plot3d()
- car::scatter3d()
library(rgl)
attach(mtcars)
plot3d(wt,disp,mpg,col="red",size=5)library(car)
attach(mtcars)
scatter3d(wt,disp,mpg)4.气泡图
attach(mtcars)
r=sqrt(disp/pi)
symbols(wt,mpg,circles = r,inches = 0.30,
fg="white",bg="lightblue",
main = "Bubble Plot with point size proportional to displacement",
ylab = "Miles Per Gallon",
xlab = "Weight of Car (lbs/1000)")
text(wt,mpg,rownames(mtcars),cex = 0.6)
detach(mtcars)注意：inchs参数控制着气泡大小与数据比例，选择合适的比例可以避免可能的混乱。
5.其他绘图
5.1.绘制散点图
par(mfrow=c(1,2))
t1 <- subset(Orange, Tree==1)
plot(t1$age, t1$circumference,
xlab="Age (days)",
ylab="Circumference (mm)",
main="Orange Tree 1 Growth")
plot(t1$age, t1$circumference,
xlab="Age (days)",
ylab="Circumference (mm)",
main="Orange Tree 1 Growth",
type="b")
Orange$Tree <- as.numeric(Orange$Tree)
ntrees <- max(Orange$Tree)
xrange <- range(Orange$age)
yrange <- range(Orange$circumference)
plot(xrange, yrange,
type="n",
xlab="Age (days)",
ylab="Circumference (mm)"
)
colors <- rainbow(ntrees)
linetype <- c(1:ntrees)
plotchar <- seq(18, 18+ntrees, 1)
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]
)
}
title("Tree Growth", "example of line plot")
legend(xrange[1], yrange[2],
1:ntrees,
cex=0.8,
col=colors,
pch=plotchar,
lty=linetype,
title="Tree"
) 
5.2.绘制相关图
options(digits = 2)
cor(mtcars)## mpg cyl disp hp drat wt qsec vs am gear carb
## mpg 1.00 -0.85 -0.85 -0.78 0.681 -0.87 0.419 0.66 0.600 0.48 -0.551
## cyl -0.85 1.00 0.90 0.83 -0.700 0.78 -0.591 -0.81 -0.523 -0.49 0.527
## disp -0.85 0.90 1.00 0.79 -0.710 0.89 -0.434 -0.71 -0.591 -0.56 0.395
## hp -0.78 0.83 0.79 1.00 -0.449 0.66 -0.708 -0.72 -0.243 -0.13 0.750
## drat 0.68 -0.70 -0.71 -0.45 1.000 -0.71 0.091 0.44 0.713 0.70 -0.091
## wt -0.87 0.78 0.89 0.66 -0.712 1.00 -0.175 -0.55 -0.692 -0.58 0.428
## qsec 0.42 -0.59 -0.43 -0.71 0.091 -0.17 1.000 0.74 -0.230 -0.21 -0.656
## vs 0.66 -0.81 -0.71 -0.72 0.440 -0.55 0.745 1.00 0.168 0.21 -0.570
## am 0.60 -0.52 -0.59 -0.24 0.713 -0.69 -0.230 0.17 1.000 0.79 0.058
## gear 0.48 -0.49 -0.56 -0.13 0.700 -0.58 -0.213 0.21 0.794 1.00 0.274
## carb -0.55 0.53 0.39 0.75 -0.091 0.43 -0.656 -0.57 0.058 0.27 1.000library(corrgram)
corrgram(mtcars,order = TRUE,
lower.panel = panel.shade,
upper.panel = panel.pie,
text.panel = panel.txt,
main="Corrgram of mtcats intercorrelations")
corrgram(mtcars,order = TRUE,
lower.panel = panel.ellipse,
upper.panel = panel.pts,
text.panel = panel.txt,
diag.panel = panel.minmax,
main="Corrgram of mtcats data using scatter plots and ellipse")
corrgram(mtcars,order = TRUE,
lower.panel = panel.shade,
upper.panel = NULL,
text.panel = panel.txt,
main="Car Mileage Data(unsorted)")
相关图参数设置：
- order:是否按照主成分分析结果对变量排序
- panel:绘制图形类型
- upper:上三角绘图类型
- lower:下三角绘图类型
- text:对角线标注类型
- diag:给出最大最小标注
下面使用colorRampPallette函数来改变图形颜色：
library(corrgram)
cols=colorRampPalette(c("darkgoldenrod4","burlywood1","darkkhaki","darkgreen"))
corrgram(mtcars,order = TRUE,col.regions = cols,
lower.panel = panel.shade,
upper.panel = panel.conf,
text.panel = panel.text,
main="A Corrgram of a Different Color")
5.3 马赛克图
ftable(Titanic)## Survived No Yes
## Class Sex Age
## 1st Male Child 0 5
## Adult 118 57
## Female Child 0 1
## Adult 4 140
## 2nd Male Child 0 11
## Adult 154 14
## Female Child 0 13
## Adult 13 80
## 3rd Male Child 35 13
## Adult 387 75
## Female Child 17 14
## Adult 89 76
## Crew Male Child 0 0
## Adult 670 192
## Female Child 0 0
## Adult 3 20library(vcd)
mosaic(Titanic,shade = TRUE,legend=TRUE)
mosaic(~Class+Sex+Age+Survived,data = Titanic,shade=TRUE,legend=TRUE)