barplot条形图
barplot(height, ...)
## Default S3 method:
barplot(height, width = 1, space = NULL,
names.arg = NULL, legend.text = NULL, beside = FALSE,
horiz = FALSE, density = NULL, angle = 45,
col = NULL, border = par("fg"),
main = NULL, sub = NULL, xlab = NULL, ylab = NULL,
xlim = NULL, ylim = NULL, xpd = TRUE, log = "",
axes = TRUE, axisnames = TRUE,
cex.axis = par("cex.axis"), cex.names = par("cex.axis"),
inside = TRUE, plot = TRUE, axis.lty = 0, offset = 0,
add = FALSE, args.legend = NULL, ...)
height是一个向量或者一个矩阵
width 是bar宽度向量，除非指定了xlim，否则指定单个值将没有任何可见的效果。
space 每个bar前面空出的空间。If height is a matrix and beside is TRUE，那么空间可以由两个数字指定，其中第一个是相同组中的条之间的空间，第二个是组之间的空间。
beside
a logical value. If FALSE, the columns of height are portrayed as stacked bars, and if TRUE the columns are portrayed as juxtaposed bars.【见例子中的区别】
> library(vcd)
载入需要的程辑包：grid
> counts<- table(Arthritis$Improved)
> counts
None Some Marked
42 14 28
> barplot(counts, main="simple bar plot")
> barplot(counts, main="simple bar plot", horiz = TRUE)
【horiz = TRUE】就是上面两个图的区别
> opar <- par(no.readonly = TRUE)
> par(mfrow=c(2,1))
> barplot(counts, main="simple bar plot")
> barplot(counts, main="simple bar plot", horiz = TRUE)
> par(opar)
> opar <- par(no.readonly = TRUE)
> par(mfrow=c(1,2))
> barplot(counts, main="simple bar plot")
> barplot(counts, main="simple bar plot", horiz = TRUE)
> par(opar)
| > counts <- table(Arthritis$Improved, Arthritis$Treatment) > counts
Placebo Treated None 29 13 Some 7 7 Marked 7 21 > counts1 <- table(Arthritis$Improved, Arthritis$Treatment) > counts2 <- table(Arthritis$Treatment, Arthritis$Improved) > opar<- par(no.readonly = TRUE) > par(mfrow=c(2,2)) > barplot(counts1, xlab="Treatment", ylab="Improved", legend=rownames(counts1)) > barplot(counts1, xlab="Treatment", ylab="Improved", legend=rownames(counts1), beside=TRUE) > barplot(counts2, xlab="Treatment", ylab="Improved", legend=rownames(counts2)) > barplot(counts2, xlab="Treatment", ylab="Improved", legend=rownames(counts2), beside=TRUE) > par(opar) |
barplot with aggregate均值条形图
此时就是要使用aggregate来计算每个不同分组的均值
> means <- aggregate(sta$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$x),]
> means
Group.1 x
3 North Central 0.700000
1 Northeast 1.000000
4 West 1.023077
2 South 1.737500
> means <- aggregate(sta$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$Group.1 , main = "order meanx")
spine棘状图
使用vcd包中的spine()绘制
> library(vcd)
> attach(Arthritis)
> counts <- table(Treatment, Improved)
> spine(counts, main = "Spinogram Example")
> detach(Arthritis)
pie/fan.splot饼图
pie(x, labs)
par(mfrow=c(2,2))
slices <- c(10, 12, 4, 16, 8)
lbls <- c("US", "UK", "Asutralia", "Gremany", "France")
pie(slices, labels = lbls, main = "pie chart")
pct <- round(slices/sum(slices)*100)
lbl2 <- paste(lbls, " :", pct, seq="")
pie(pct, labels = lbl2, col=rainbow(length(lbl2)), main = "pct pie chart")
install.packages("plotrix")
library(plotrix)
pie3D(slices, labels=lbl2, explode=0.1, labelcex=0.8, main="3D pie char")
mytable<- table(state.region)
pie(mytable, labels = names(mytable), main="table to pie chart")
fan.plot扇形图
slices <- c(10, 12, 4, 16, 8)
lbls <- c("US", "UK", "Asutralia", "Gremany", "France")
fan.plot(slices, labels = lbls, main="Fan plot chart")
> lbls <- paste(lbls, ": ", slices, seq=" ")
> lbls
[1] "US : 10 " "UK : 12 " "Asutralia : 4 "
[4] "Gremany : 16 " "France : 8 "
> fan.plot(slices, labels = lbls, main="Fan plot chart")
hist直方图
hist(x)
x是一个有数据值组成的数据向量
参数freq=FALSE，表示根据概率密度二不是频数绘制图形
breaks 用于控制组的数量
par(mfrow=c(2,2))
attach(mtcars)
hist(mpg)
hist(mpg, breaks = 12, xlab = "Mile per Gallon")
hist(mpg, freq=FALSE, breaks = 12, col="red", xlab = "Mile per Gallon")
rug(jitter(mpg))
lines(density(mpg), col="blue", lwd=2)
h <- hist(mpg, breaks = 12, col = "red")
xfit<-seq(min(mpg), max(mpg), length=40)
yfit <- dnorm(xfit, mean =mean(mpg), sd = sd(mpg))
yfit <- yfit*diff(h$mids[1:2]*length(mpg))
lines(xfit, yfit, col="blue", lwd=2)
box()
plot(density())核密度图
核密度估计适用于估计随机便利概率密度函数的一种非参数方法
核密度图不失为一种用来观测连续型变量分布的有效方法
绘制核密度图的方法（不叠加到另一幅图上方）为：
plot(density())
attach(mtcars)
par(mfrow=c(3,1))
d <- density(mpg)
plot(d)
plot(d, main="Kernel Density of miles Per Gallon")
polygon(d, col="red", border="blue")
plot(d, main="Kernel Density of miles Per Gallon")
polygon(d, col="red", border="blue")
rug(mtcars$mpg, col="brown")
这三幅图中能很好的区分每个函数是干嘛的
polygon 根据x与y坐标绘制多边形，是个中间区域染色，形成密度块
rug是刻度须函数
使用sm包中的sm.density.compare()函数可以向图形叠加两组或者更多的核密度图
sm.density.compare(x, factor)
x是一个数值型向量，factor是一个分组变量
par(lwd=2)
library(sm)
attach(mtcars)
cyl.f <- factor(cyl, levels=c(4,6,8), labels = c("4 cyl", "6 cyl", "8 cyl"))
sm.density.compare(mpg, cyl)
colfill <- c(2:(1+length(levels(cyl.f))))
colfill
legend(locator(1), levels(cyl.f), fill=colfill)
locator(1) 是通过单击鼠标来确定legend的位置
这个legend是通过单击鼠标确定的位置
boxplot箱线图
箱线图通过绘制连续型变量的5个数总括，即最小值，25%, 50%, 75% ， 最大值，描述了连续型变量的分布。
箱线图能够显示出可能为离群点（范围±1.5*IQR以外的值，IQR表示4分为距，即上四分位与下四分位数的差值）的观测值
boxplot(x, ...) ## S3 method for class 'formula' boxplot(formula, data = NULL, ..., subset, na.action = NULL, drop = FALSE, sep = ".", lex.order = FALSE) ## Default S3 method: boxplot(x, ..., range = 1.5, width = NULL, varwidth = FALSE, notch = FALSE, outline = TRUE, names, plot = TRUE, border = par("fg"), col = NULL, log = "", pars = list(boxwex = 0.8, staplewex = 0.5, outwex = 0.5), horizontal = FALSE, add = FALSE, at = NULL) |
boxplot(mpg~cyl, data=mtcars)
按照cyl进行分组统计data=mtcars的数据
boxplot(formula, data=dataframe)
formula 是一个公式
dataframe代表提供数据的数据库或列表
一个公式 y~A ， 这将为类别变量A的每个值并列地生成变量y的箱线图
公式y~ A*B 则将为类别型变量A和B所有水平的两两组合生产数值型变量y的箱线图
varwidth= TRUE
将使用箱线图的宽度与其样本大小的平方根成正比
参数horizontal =TRUE 可以反转坐标轴的方向
notch=TRUE 则是箱线图中生成凹槽， 中位数
boxplot(mpg~cyl, data=mtcars, notch=TRUE， col=”red”)
boxplot(mpg~cyl*am, data=mtcars, col="red")
vioplot小提琴图
vioplot
library(vioplot)
x1 <- mpg[cyl=4]
x1 <- mpg[cyl==4]
x1
[1] 22.8 24.4 22.8 32.4 30.4 33.9 21.5 27.3 26.0 30.4 21.4
x2 <- mpg[cyl ==6]
x3 <- mpg[cyl ==8]
vioplot(x1, x2, x3, names = c("4 cyl", "6 cyl", "8 cyl"))
vioplot(x1, x2, x3, names = c("4 cyl", "6 cyl", "8 cyl"), col="gold")
小提琴图时候箱线图与核密图的结合
x1, x2…..表示要绘制的一个或者多个向量
参数names 是小提琴图中标签的字符向量
白点是中位数，黑色盒型的范围是下4分位点到上4分位点，细黑线表示须，外部形状记为核密度估计
dotchart点图
dotchart(x, labels)