scatter.jpg

3. 散点图

[TOC]

22

散点图通常用于刻画两个连续型变量之间的关系。绘制散点图时，数据集中的每一个观测值都由每个点表示。

3.1 绘制基本散点图

library(gcookbook) 
library(ggplot2)
# 列出我们用到的列
head(heightweight[, c("ageYear", "heightIn")])

> head(heightweight[, c("ageYear", "heightIn")])
  ageYear heightIn
1   11.92     56.3
2   12.92     62.3
3   12.75     63.3
4   13.42     59.0
5   15.92     62.5
6   14.25     62.5

ggplot(heightweight, aes(x=ageYear, y=heightIn)) + geom_point()

unnamed-chunk-11

# shape参数设置点型 size设置点的大小
ggplot(heightweight, aes(x=ageYear, y=heightIn)) + 
  geom_point(shape=21)
ggplot(heightweight, aes(x=ageYear, y=heightIn)) + 
  geom_point(size=1.5)

image-20210816225649979

3.2 使用点形和颜色属性进行分组

head(heightweight[, c("sex", "ageYear", "heightIn")])
> head(heightweight[, c("sex", "ageYear", "heightIn")])
  sex ageYear heightIn
1   f   11.92     56.3
2   f   12.92     62.3
3   f   12.75     63.3
4   f   13.42     59.0
5   f   15.92     62.5
6   f   14.25     62.5

ggplot(heightweight, aes(x=ageYear, y=heightIn, colour=sex)) + 
  geom_point()
ggplot(heightweight, aes(x=ageYear, y=heightIn, shape=sex)) + 
  geom_point()

unnamed-chunk-14 unnamed-chunk-15

# scale_shape_manual()使用其它点形状
#scale_colour_brewer()使用其它颜色
ggplot(heightweight, aes(x=ageYear, y=heightIn, shape=sex, colour=sex)) +
  geom_point() +
  scale_shape_manual(values=c(1,2)) +
  scale_colour_brewer(palette="Set1")

unnamed-chunk-17

3.3 使用不同于默认设置的点形

# 使用点形和填充色属性分别表示不同变量
hw <- heightweight
# 分组 Categorize into <100 and >=100 groups
hw$weightGroup <- cut(hw$weightLb, breaks=c(-Inf, 100, Inf),
                      labels=c("< 100", ">= 100"))

# 使用具有颜色和填充色的点形及对应于空值(NA)和填充色的颜色
ggplot(hw, aes(x=ageYear, y=heightIn, shape=sex, fill=weightGroup)) +
  geom_point(size=2.5) +
  scale_shape_manual(values=c(21, 24)) +
  scale_fill_manual(values=c(NA, "black"),
                    guide=guide_legend(override.aes=list(shape=21)))

unnamed-chunk-33

3.4 将连续型变量映射到点的颜色或大小属性上

ggplot(heightweight, aes(x=ageYear, y=heightIn, colour=weightLb)) + 
  geom_point()

ggplot(heightweight, aes(x=ageYear, y=heightIn, size=weightLb)) + 
  geom_point()

image-20210817114855294

# 默认点的大小范围为1-6mm
# scale_size_continuous(range=c(2, 5))修改点的大小范围

# 将色阶设定为由黑至白
ggplot(heightweight, aes(x=weightLb, y=heightIn, fill=ageYear)) +
  geom_point(shape=21, size=2.5) +
  scale_fill_gradient(low="black", high="white")

# 使用 guide_legend() 函数以离散的图例代替色阶
ggplot(heightweight, aes(x=weightLb, y=heightIn, fill=ageYear)) +
  geom_point(shape=21, size=2.5) +
  scale_fill_gradient(low="black", high="white", breaks=12:17,
                      guide=guide_legend())

image-20210817165620820

# 调用scale_size_area()函数使数据点的面积正比于变量值。
ggplot(heightweight, aes(x=ageYear, y=heightIn, size=weightLb, colour=sex)) +
  geom_point(alpha=.5) +
  scale_size_area() +   
  scale_colour_brewer(palette="Set1")

unnamed-chunk-45

3.5 处理图形重叠

方法：

• 使用半透明的点
• 将数据分箱(bin)，并用矩形表示
• 将数据分箱(bin)，并用六边形表示
• 使用箱线图

sp <- ggplot(diamonds, aes(x=carat, y=price))
sp + geom_point()
# 透明度
sp + geom_point(alpha=.1)
sp + geom_point(alpha=.01)

# stat_bin2d()函数默认分别在x轴和y轴方向上将数据分割为30各组
sp + stat_bin2d()

# bin=50设置箱数,limits参数设定图例范围
sp + stat_bin2d(bins=50) +
  scale_fill_gradient(low="lightblue", high="red", limits=c(0, 6000))

image-20210817173245460

# stat_binhex()函数使用六边形分箱
library(hexbin)
sp + stat_binhex() +
  scale_fill_gradient(low="lightblue", high="red",
                      limits=c(0, 8000))

sp + stat_binhex() +
  scale_fill_gradient(low="lightblue", high="red",
                      breaks=c(0, 250, 500, 1000, 2000, 4000, 6000),
                      limits=c(0, 6000))

image-20210817174431437

sp1 <- ggplot(ChickWeight, aes(x=Time, y=weight))

sp1 + geom_point()
# 调用position_jitter()函数给数据点增加随机扰动,通过width,height参数调节
sp1 + geom_point(position="jitter")
# 也可以调用 geom_jitter()
sp1 + geom_point(position=position_jitter(width=.5, height=0))

image-20210817175225507

# 箱线图
sp1 + geom_boxplot(aes(group=Time))

unnamed-chunk-511

参考书籍

• R Graphics Cookbook, 2nd edition.