ggplot2-绘制散点图

本文更新地址:http://blog.csdn.net/tanzuozhev/article/details/51106909

本文在 http://www.cookbook-r.com/Graphs/Scatterplots_(ggplot2)/ 的基础上加入了自己的理解

数据

set.seed(955) # 设置随机种子, 设置种子之后可以很容易的得到相同的随机数据
# Make some noisily increasing data
dat <- data.frame(cond = rep(c("A", "B"), each=10),
                  xvar = 1:20 + rnorm(20,sd=3),
                  yvar = 1:20 + rnorm(20,sd=3))
head(dat)

##   cond      xvar         yvar
## 1    A -4.252354  3.473157275
## 2    A  1.702318  0.005939612
## 3    A  4.323054 -0.094252427
## 4    A  1.780628  2.072808278
## 5    A 11.537348  1.215440358
## 6    A  6.672130  3.608111411

library(ggplot2)

带有回归线的散点图

# xvar为横坐标, yvar为纵坐标
ggplot(dat, aes(x=xvar, y=yvar)) +
    geom_point(shape=1)      # 空心圆

ggplot(dat, aes(x=xvar, y=yvar)) +
    geom_point(shape=1) +    # Use hollow circles
    geom_smooth(method=lm)   # 添加线性回归线

                             #  灰色阴影部分为95%置信区间
ggplot(dat, aes(x=xvar, y=yvar)) +
    geom_point(shape=1) +    # Use hollow circles
    geom_smooth(method=lm,   
                se=FALSE)    # 不添加置信区间

ggplot(dat, aes(x=xvar, y=yvar)) +
    geom_point(shape=1) +    # Use hollow circles
    geom_smooth()            

## geom_smooth: method="auto" and size of largest group is <1000, so using loess. Use 'method = x' to change the smoothing method.

设置颜色

# 根据 cond 设置颜色
ggplot(dat, aes(x=xvar, y=yvar, color=cond)) + geom_point(shape=1)

# Same, but with different colors and add regression lines
ggplot(dat, aes(x=xvar, y=yvar, color=cond)) +
    geom_point(shape=1) +
    scale_colour_hue(l=50) + # 设置颜色, l表示 亮度
    geom_smooth(method=lm,   #回归线
                se=FALSE)    

ggplot(dat, aes(x=xvar, y=yvar, color=cond)) + geom_point(shape=1) +
    scale_colour_hue(l=50) + # 设置亮度
    geom_smooth(method=lm,   #回归线
                se=FALSE,    # Don't add shaded confidence region
                fullrange=TRUE) # 延伸回归线

# 根据 cond 设置形状
ggplot(dat, aes(x=xvar, y=yvar, shape=cond)) + geom_point()

ggplot(dat, aes(x=xvar, y=yvar, shape=cond)) + geom_point() +
    scale_shape_manual(values=c(1,2))  # 手动设置形状(自定义)

重叠数据的处理

# Round xvar and yvar to the nearest 5
dat$xrnd <- round(dat$xvar/5)*5
dat$yrnd <- round(dat$yvar/5)*5

# 设置透明, 重叠的地方越多,颜色越重
# Make each dot partially transparent, with 1/4 opacity
# For heavy overplotting, try using smaller values
ggplot(dat, aes(x=xrnd, y=yrnd)) +
    geom_point(shape=19,      # Use solid circles
               alpha=1/4)     # 1/4 opacity

# 重叠的地方设置扰动(在重叠的位置周围扰动)
# Jitter the points
# Jitter range is 1 on the x-axis, .5 on the y-axis
ggplot(dat, aes(x=xrnd, y=yrnd)) +
    geom_point(shape=1,      # Use hollow circles
               position=position_jitter(width=1,height=.5))