这次不介绍如ggplot2等绘图包, 只记录一些R基础就能实现的东西~
跟着我爪子敲一遍，相信你会有收获！
有用的话请点赞收藏┗|｀O′|┛ 嗷~~
能点个大大的关注就更感谢了 !! Orz~
!!!多图
流量预警
x <- c(1,2,3,4)
y <- c(5,1,2,9)
plot(x,y)
plot(x)
y <- factor(c("a","b","c","b","a","a","a","C","c"))
plot(y)
a <- sample(c("a","b","c"), 10, replace=T)
a
## [1] "b" "b" "c" "a" "b" "b" "a" "a" "b" "b"
f <- factor(a)
f
## [1] b b c a b b a a b b
## Levels: a b c
plot(f)
举个栗子
par(mfrow=c(1,3))
a <- sample(1:100, 100, replace = T)
a
## [1] 30 73 45 64 62 52 79 72 82 10 28 46 90 99 1 89 24 32
## [19] 74 97 47 55 19 20 64 10 36 7 87 98 35 58 82 52 13 39
## [37] 21 7 40 34 69 54 92 34 5 34 13 36 5 92 10 67 67 39
## [55] 3 22 23 81 95 16 33 10 69 84 53 25 79 28 88 16 83 75
## [73] 76 58 100 32 98 13 50 12 93 87 95 3 57 87 7 31 16 49
## [91] 61 71 47 37 14 11 83 75 29 38
boxplot(a)
如果你不懂par的用法
?par然后就会在Rstudio右下角出现帮助信息
然后par(mfrow=c(1,3))的意思就是一个图版显示1行3列
添加几个异常值
b <- c(a, -180:-190, 181:180)
boxplot(b)
这样就看到在max最大值之上,min最小值之下,都有一些“离群点”
接下来引用R自带的一个数据集InsectSprays
class(InsectSprays)
## [1] "data.frame"
summary(InsectSprays)
## count spray
## Min. : 0.00 A:12
## 1st Qu.: 3.00 B:12
## Median : 7.00 C:12
## Mean : 9.50 D:12
## 3rd Qu.:14.25 E:12
## Max. :26.00 F:12
InsectSprays
## count spray
## 1 10 A
## 2 7 A
## 3 20 A
## 4 14 A
## 5 14 A
## 6 12 A
## 7 10 A
## 8 23 A
## 9 17 A
## 10 20 A
## 11 14 A
## 12 13 A
## 13 11 B
## 14 17 B
# ……太长略过
## 69 26 F
## 70 26 F
## 71 24 F
## 72 13 F
# 注意,~表示因果关系,这里的意思是横坐标(自变量)为count,纵坐标(因变量)为spray
boxplot(count~spray, data=InsectSprays)
加上颜色
boxplot(count~spray, data=InsectSprays, col=2:7)
进阶的boxplot
boxplot(count~spray, data = InsectSprays, col = "lightgray")
boxplot(count~spray, data = InsectSprays, col = "lightgray")
boxplot(count~spray, data=InsectSprays,notch=T, add=T, col=2:7)
## Warning in bxp(list(stats = structure(c(7, 11, 14, 18.5, 23, 7, 12, 16.5, : some
## notches went outside hinges ('box'): maybe set notch=FALSE
# notch关键字: 保证我绘的图有凹进去的一小块
# add关键字: 将图画在原来的图之上
plot将第一个参数输入为factor就可以画箱图
par(mfrow=c(1,2))
y <- c(10,506,140,200)
x <- c(1,2,1,2)
plot(x,y)
a <- y
b <- x
b <- as.factor(b)
plot(b,a)
下面实现这张图
y <- c(88,99,66,77,88,97,33,55,66,99,88,99,77,55,66,77,98,99,96,90,80)
y
## [1] 88 99 66 77 88 97 33 55 66 99 88 99 77 55 66 77 98 99 96 90 80
f <- factor(c(rep("班级1",6), rep("班级2",3), rep("班级3",5), rep("班级4",7)))
f
## [1] 班级1 班级1 班级1 班级1 班级1 班级1 班级2 班级2 班级2 班级3 班级3 班级3
## [13] 班级3 班级3 班级4 班级4 班级4 班级4 班级4 班级4 班级4
## Levels: 班级1 班级2 班级3 班级4
plot(f,y)
df <- data.frame(
age=c(10,12,13),
height=c(150,160,170),
weight=c(50,60,70)
)
df
## age height weight
## 1 10 150 50
## 2 12 160 60
## 3 13 170 70
plot(df)
plot(~age+height,data=df)
plot(weight~age+height, data=df)
x <- matrix(1:9, nrow = 3)
x
## [,1] [,2] [,3]
## [1,] 1 4 7
## [2,] 2 5 8
## [3,] 3 6 9
pairs(x)
x <- matrix(1:10, nrow = 2)
x
## [,1] [,2] [,3] [,4] [,5]
## [1,] 1 3 5 7 9
## [2,] 2 4 6 8 10
pairs(x)
所以一列就是一个分量var
x <- matrix(1:10, nrow = 5)
x
## [,1] [,2]
## [1,] 1 6
## [2,] 2 7
## [3,] 3 8
## [4,] 4 9
## [5,] 5 10
pairs(x)
这里就是两个分量var
a <- c("a","b","a","b","a","b")
n1 <- c(1,2,3,4,5,6)
n2 <- c(100,200,300,400,500,600)
df <- data.frame(a,n1,n2)
df
## a n1 n2
## 1 a 1 100
## 2 b 2 200
## 3 a 3 300
## 4 b 4 400
## 5 a 5 500
## 6 b 6 600
coplot(n1~n2|a)
意思就是n1做纵坐标(因变量), 左边是含有“a”字符的feature的n2的值作为横坐标(自变量),右边是含有“b”的n2值作为横坐标
所以coplot可以绘制的就是,在给定一个feature,这里是factor a的情况下,分别绘制另外两个feature(这里是n1,n2)之间的关系
data <- c(rep(1,20),rep(2,11),rep(3,6))
hist(data,breaks = c(0.5,1.5,2.5,3.5))
beaks断点,控制直方图每个方形的起始 下面了解freq,控制显示Frequency频次还是Density频率, main控制title
par(mfrow=c(1,2))
hist(data,breaks = c(0.5,1.5,2.5,3.5), freq = T, main="freq=T")
hist(data,breaks = c(0.5,1.5,2.5,3.5), freq = F, main="freq=F")
太丑了,加颜色
par(mfrow=c(1,2))
hist(data,breaks = c(0.5,1.5,2.5,3.5), freq = T, main="freq=T",col = "red")
hist(data,breaks = c(0.5,1.5,2.5,3.5), freq = F, main="freq=F",col = rainbow(3))
这里引用R自带的数据VADeaths,为Virginia州在1940年的人口死亡率
VADeaths
## Rural Male Rural Female Urban Male Urban Female
## 50-54 11.7 8.7 15.4 8.4
## 55-59 18.1 11.7 24.3 13.6
## 60-64 26.9 20.3 37.0 19.3
## 65-69 41.0 30.9 54.6 35.1
## 70-74 66.0 54.3 71.1 50.0
dotchart(VADeaths)
- axes=FALSE: 表示图形没有坐标轴
- axes默认为TRUE
x <- 1:100
y <- rnorm(100)
par(mfrow=c(1,2))
plot(x,y)
plot(x,y,axes=F)
- log = “x”: 表示对x轴的数据取对数
- log = “y”: 表示对y轴的数据取对数
- log = “xy”: 表示对x轴y轴的数据同时取对数
x <- c(100:400)
y <- c(100:400)
par(mfrow=c(2,2))
plot(x,y,main = "no log")
plot(x,y,log="x", main = "logX")
plot(x,y,log="y", main = "logY")
plot(x,y,log="xy",main = "logX, logY")
要注意的是! 坐标轴上的值没有log处理, 但是scale发生了变化,注意看第一个图和其他图的坐标轴的scale差别!
再举一个例子
y <- rnorm(100,mean = 1,sd = 0.2)
y
## [1] 0.8980091 0.6852322 1.2044800 1.2776998 1.2134941 1.5039153 1.0459592
## [8] 0.9735094 0.9632086 0.7840762 0.9561820 1.0682900 1.2299661 0.7964328
## [15] 1.2501282 1.2538794 1.1110020 1.1281667 0.9146932 1.1525602 0.9235296
## [22] 1.2587914 1.1502627 0.8474249 0.8605189 0.7996569 0.7705961 1.0117431
## [29] 1.0216131 0.7203251 0.9868219 1.0719735 1.0109386 0.9261525 1.0817812
## [36] 0.8693676 1.0760423 0.9864053 1.1460755 1.0351856 0.8639127 0.8492640
## [43] 0.7028910 0.9551903 0.9944747 0.9613023 1.0191328 1.3326953 1.0689955
## [50] 1.0532902 1.0196450 0.9958206 1.1413616 1.1432881 1.0067486 0.8076296
## [57] 0.9381742 0.9088661 1.0080376 1.1991312 0.9870369 0.6442198 0.9884344
## [64] 0.7986086 0.9030633 1.2628671 0.9356189 0.8920940 1.3426112 0.6536987
## [71] 0.9891035 0.8206377 1.2027576 1.1888137 1.1056899 0.4963600 0.7903617
## [78] 1.2959905 0.9425905 1.4026465 0.8265211 0.7913631 0.9399355 1.3695836
## [85] 0.7709729 1.1433862 0.8246760 1.2058195 0.8117328 1.2648799 1.0891554
## [92] 1.5258819 1.0580903 1.0592030 1.0821120 0.8887973 0.8354623 1.2193486
## [99] 0.9504487 1.1167717
x <- 1:100
x
## [1] 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18
## [19] 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36
## [37] 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54
## [55] 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72
## [73] 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90
## [91] 91 92 93 94 95 96 97 98 99 100
par(mfrow=c(2,2))
plot(x,y,main="no log")
plot(x,y,log="x", main = "logX")
plot(x,y,log="y", main = "logY")
plot(x,y,log = "xy",main = "logX, logY")
从no log图可以看到,数据都是集中在0.6~1.4之间的,对x取log之后发现,大量的数据是集中在1附近的,这个在no log图中就看不太明显,logxlogy同理,而logy就看不太明显
type = ?
x <- 1:20
y <- sample(1:100, 20)
par(mfrow=c(2,2))
plot(x,y,main = "p",type = "p")
plot(x,y,main = "l",type = "l")
plot(x,y,main = "b",type = "b")
plot(x,y,main = "o",type = "o")
par(mfrow=c(2,2))
plot(x,y,main = "h",type = "h")
plot(x,y,main = "s",type = "s")
plot(x,y,main = "n",type = "n")
x <- 1:20
y <- sample(1:1000, 20)
par(mfrow=c(1,2))
plot(x,y)
plot(x,y,xlab = "this is X label", ylab = "this is Y label", main = "this is main/title", sub = "this is sub title of the sub plot")
x <- c(1:10)
y <- sample(1:200, 10)
z <- sample(150:300, 10)
par(mfrow=c(2,1))
plot(x,y,type="l")
plot(x,z,type = "l")
上面是绘制成了两个图
x <- c(1:10)
y <- sample(1:200, 10)
z <- sample(150:300, 10)
plot(x,y,type="l")
points(x,z,type = "l",col="red")
但是有一些z的值超出范围了（仔细看左上角的小红线）,咋整呢?看下面
x <- c(1:10)
y <- sample(1:200, 10)
z <- sample(150:300, 10)
plot(x,y,type="l",ylim=c(0,300))
points(x,z,type = "l",col="red")
x <- c(1:10)
y <- sample(1:200, 10)
z <- sample(150:300, 10)
plot(x,y,type="l",ylim=c(0,300))
points(x,z,type = "p",col="red")
当然也可以更改type让红线变成点或者其他样式
x <- c(1:10)
y <- sample(1:200, 10)
z <- sample(150:300, 10)
plot(x,y,type="l",ylim=c(0,300))
lines(x,z,type = "l",col="red")
x <- c(1:10)
y <- sample(1:200, 10)
z <- sample(150:300, 10)
plot(x,y,type="l",ylim=c(0,300))
lines(x,z,type = "b",col="red")
x <- c(1:10)
y <- sample(1:200, 10)
z <- sample(150:300, 10)
plot(x,y,type="l",ylim=c(0,300))
lines(x,z,type = "h",col="red")
x <- c(1:10)
y <- sample(1:200, 10)
z <- sample(150:300, 10)
plot(x,y,type="l",ylim=c(0,300))
lines(x,z,type = "s",col="red")
x <- 1:20
y1 <- sample(1:1000,20)
y2 <- sample(1:1000,20)
plot(x,y1,type = "l")
par(new=TRUE)
plot(x,y2,col="red",type = 'o')
x <- 1:20
y1 <- sample(1:1000,20)
y2 <- sample(1:1000,20)
plot(x,y1,type = "l")
par(new=TRUE)
plot(x,y1,col="red",type = 'p')
所以我们通过这种办法就得到了黑线和红点的结合!
接下来画我们的封面图！
x <- 1:20
y1 <- sample(1:1000,20)
plot(x,y1,type = "l",col="red",lwd=10)
plot(x,y1,type="l",col="yellow",lwd=5)
神奇的结果出现了!
plot(x,y1,type = "l",col="red",lwd=10)
par(new=TRUE)
plot(x,y1,type="l",col="yellow",lwd=5)
Beautiful!
下图的细节 - type=“n”: 不绘点! - text(x,y)
x <- 1:20
y <- sample(1:10000000000, 20)
plot(x,y,type = "n")
text(x,y)
x <- c(1:5)
y <- c(6:10)
plot(x,y,type = "b")
text(x,y)
可以看到有个问题是字和点重合了看不清楚
x <- c(1:5)
y <- c(6:10)
plot(x,y,type = "b")
text(x+0.1,y-0.05)
这样就好看多了!
x <- c(1:5)
y <- c(6:10)
plot(x,y,type = "b")
text(x+0.1,y-0.05, labels = c("A","B","C","D"))
这里的细节是,labels来自定义值,但是看到有五个点我们只定义了4个所以,最后一个触发了R的自动补齐,也就是repeat了这个向量,也就是从A又开始了
plot(1:5,1:5)
abline(h=4,col="blue",lty=3)
abline(h=2)
abline(v=1,col="red",lty=2)
abline(v=4.5,lty=4,col=9)
abline(-3,3, lty=1) # y = 3x-3
细节可以?abline查看帮助文档嗷
x <- 1:10
y <- rnorm(x)
plot(x,y,type="l")
x <- 1:10
y <- rnorm(x)
x1 <- c(2,4,4,2)
y1 <- c(0,0,1,1)
plot(x,y,type="l")
polygon(x1,y1,col = 'pink',)
x <- 1:10
y <- rnorm(x)
x1 <- c(2,4,4,2)
y1 <- c(0,0,1,1)
plot(x,y,type="l")
polygon(x1,y1,col = 'yellow', border = 5,lty = 10)
同,了解更多使用?polygon
x <- 1:10
y <- rnorm(x)
x1 <- c(2,4,4,2)
y1 <- c(0,0,1,1)
plot(x,y,type="l")
polygon(x1,y1,col = 'pink',)
title("this is a title")
那么有人要问title和main sub的区别呢? 还是这个图,我画两次
x <- 1:10
y <- rnorm(x)
x1 <- c(2,4,4,2)
y1 <- c(0,0,1,1)
par(mfrow=c(1,2))
plot(x,y,type="l",main = "this is main 1",sub = "this is sub1")
polygon(x1,y1,col = 'pink')
plot(x,y,type="l", main = "this is main 2", sub = 'this is sub2')
polygon(x1,y1,col = 'black')
par(new=TRUE,mfrow=c(1,1))
title("this is a title")
这样子是不是理解了, 先画了一个含有俩子图的图,俩子图都有各自的main和sub 然后这时候不能直接title,直接title默认是和this is main2这个位置冲叠的, 可以试试! 画到中间的位置思路就是新开一个重叠画布
axis(side,…) - 1: 底部 - 2: 左侧 - 3: 顶部 - 4: 右侧 axis一般需要和axes=F搭配使用
x <- 1:10
y <- rnorm(x)
par(mfrow=c(2,2))
plot(x,y,type="l",axes = F); axis(1)
plot(x,y,type="l",axes = F); axis(2)
plot(x,y,type="l",axes = F); axis(3)
plot(x,y,type="l",axes = F); axis(4)
x <- c(1:10)
y <- sample(1:100,10)
par(mfrow=c(2,2))
plot(x,y)
plot(x,y,xlim=c(4,8))
plot(x,y,ylim=c(0,50))
plot(x,y,xlim = c(1,5),ylim = c(50,80))
编辑于 07-29