ggplot2教程，从入门到精通（一）

数据清洗中的10个高频操作！

2024-12-11

纯生信适合入门，高阶生信分析和数据挖掘仍需要 R 语言或 Python。为此我们不断完善教程，相继推出了纯生信21天，R 语言21天和单细胞21天。但是，数据处理的核心部分并没有变，数据清洗+数据可视化！前面分享了数据清洗 tidyverse 包中的10个高频操作，接下来，我们重点分享 ggplot2 包中的理论和实操！

# 映射的相关参数，榴莲整理，特此感谢！aes()函数中常见的映射选项是：    x和y：用于指定x轴和y轴映射的变量    color：映射点或线的颜色    fill：映射填充区域的颜色    linetype：映射图形的线形（1=实线、2=虚线、3=点、4=点破折号、5=长破折号、6=双破折号）    size：点的尺寸和线的宽度    shape：映射点的形状

## 加载包和数据
library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.1     ✔ tibble    3.2.1
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.0.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(ggplot2)

load(file = "test.rds")

## 基本绘图

(g <- ggplot(exprSet1, aes(x = GSM180994, y = GSM180995)))

g + geom_point()

g + geom_line()

g + geom_line() + geom_point()

# 调整几何图形的属性
g + geom_point(color = "firebrick", shape = "diamond", size = 2)

g + geom_point(color = "firebrick", shape = "diamond", size = 2) +
  geom_line(color = "firebrick", linetype = "dotted", lwd = .3)

# 替换默认的ggplot2主题
theme_set(theme_bw())
g + geom_point(color = "firebrick")

## 调整坐标轴
# 修改title
ggplot(exprSet1, aes(x = GSM180994, y = GSM180995)) +  
  geom_point(color = "firebrick") +
  labs(x = "Sample No.1", y = "Sample No.2")

ggplot(exprSet1, aes(x = GSM180994, y = GSM180995)) +
  geom_point(color = "firebrick") +
  labs(x = "Sample NO.1", y = expression(paste("Sample NO.2"^"(Hey, why should we use metric units?!)")))

# 增加轴和轴标题之间的空间
ggplot(exprSet1, aes(x = GSM180994, y = GSM180995)) +
  geom_point(color = "firebrick") +
  labs(x = "Sample No.1", y = "Sample No.2") +
  theme(axis.title.x = element_text(vjust = 0, size = 15),
        axis.title.y = element_text(vjust = 2, size = 15))

ggplot(exprSet1, aes(x = GSM180994, y = GSM180995)) +
  geom_point(color = "firebrick") +
  labs(x = "Sample No.1", y = "Sample No.2") +
  theme(axis.title.x = element_text(margin = margin(t = 10), size = 15),
        axis.title.y = element_text(margin = margin(r = 10), size = 15))

# 改变轴标题的美学
ggplot(exprSet1, aes(x = GSM180994, y = GSM180995)) +
  geom_point(color = "firebrick") +
  labs(x = "Sample No.1", y = "Sample No.2") +
  theme(axis.title = element_text(size = 15, color = "firebrick",
                                  face = "italic"))

# face参数可用于使字体加粗或倾斜
ggplot(exprSet1, aes(x = GSM180994, y = GSM180995)) +
  geom_point(color = "firebrick") +
  labs(x = "Sample No.1", y = "Sample No.2") +
  theme(axis.title.x = element_text(color = "sienna", size = 15),
        axis.title.y = element_text(color = "orangered", size = 15))

# 调整坐标轴文本美学
ggplot(exprSet1, aes(x = GSM180994, y = GSM180995)) +
  geom_point(color = "firebrick") +
  labs(x = "Sample No.1", y = "Sample No.2") +
theme(axis.text = element_text(color = "dodgerblue", size = 12),
      axis.text.x = element_text(face = "italic"))

# 旋转坐标轴文本
ggplot(exprSet1, aes(x = GSM180994, y = GSM180995)) +
  geom_point(color = "firebrick") +
  labs(x = "Sample No.1", y = "Sample No.2") +
  theme(axis.text.x = element_text(angle = 30, vjust = 0, hjust = 1, size = 12))

# 删除坐标轴标题
ggplot(exprSet1, aes(x = GSM180994, y = GSM180995)) +
  geom_point(color = "firebrick") +
  labs(x = "Sample No.1", y = "Sample No.2") +
  labs(x = NULL, y = "")

# 限制坐标轴范围
ggplot(exprSet1, aes(x = GSM180994, y = GSM180995)) +
  geom_point(color = "firebrick") +
  labs(x = "Sample No.1", y = "Sample No.2") +
  ylim(c(0, 15))

# 可以使用scale_y_continuous(limits = c(0,15))或coord_cartesian(ylim = c(0,15))
  
# 使图表从坐标原点开始  
ggplot(exprSet1, aes(x = GSM180994, y = GSM180995)) +
  geom_point(color = "firebrick") +
  labs(x = "Sample No.1", y = "Sample No.2") +
  expand_limits(x = 0, y = 0)

# 相同比例的坐标轴
ggplot(exprSet1, aes(x = GSM180994, y = GSM180995)) +
  geom_point(color = "firebrick") +
  labs(x = "Sample No.1", y = "Sample No.2") +
  xlim(c(0, 15)) + ylim(c(0, 15)) +
  coord_fixed()

# 使用函数调整标签
ggplot(exprSet1, aes(x = GSM180994, y = GSM180995)) +
  geom_point(color = "firebrick") +
  labs(x = "Year", y = NULL) +
  scale_y_continuous(label = function(x) {return(paste(x, "Expression"))})

参考资料：

1. https://mp.weixin.qq.com/s/9UcZRKDe0pfh3ViJ3okC4g

2. https://zhuanlan.zhihu.com/p/370223674

3. 大神的博客：https://hadley.nz/

4. https://blog.csdn.net/huangmingleiluo/article/details/104192128

5. https://blog.csdn.net/weixin_45331620/article/details/106622445