本文参考ggpubr包官方文档https://rpkgs.datanovia.com/ggpubr/index.html及http://www.sthda.com/english/articles/24-ggpubr-publication-ready-plots/
ggpubr 包是基于ggplot2包,非R数据专业人员可用ggpubr包绘制图表
下载安装ggpubr
install.packages("ggpubr")
或者使用以下命令
if(!require(devtools)) install.packages("devtools")
devtools::install_github("kassambara/ggpubr")
ggpubr可绘制大部分我们常用的图形
- 分布图(Distribution)
- 密度分布图以及边际地毯线并添加平均值线(Density plot with mean lines and marginal rug)
- 带有均值线和边际地毯线的直方图(Histogram plot with mean lines and marginal rug)
- 箱线图和小提琴图(Box plots and violin plots)
- 具有不同点分布的箱线图(Box plots with jittered points)
- 小提琴图内添加箱线图(Violin plots with box plots inside)
- 条形图(Bar plots)
- 有序的条形图(Ordered bar plots)
- 偏差图(Deviation graphs)
- 点图 (Dot charts)
- 棒棒糖图表(Lollipop chart)
- 偏差图(Deviation graphs)
- 克利夫兰点图(Cleveland’s dot plot)
首先:
分布图——密度分布图
library(ggpubr) #加载ggubr, 同时也要安装加载ggplot2, magrittr 这两个包
#> Le chargement a nécessité le package : ggplot2
#> Le chargement a nécessité le package : magrittr
# Create some data format 设置数值
# :::::::::::::::::::::::::::::::::::::::::::::::::::
set.seed(1234)
# set.seed 用于设定随机数种子,
#一个特定的种子可以产生一个特定的伪随机序列,
#这个函数的主要目的,是让你的模拟能够可重复出现,
#因为很多时候我们需要取随机数,但这段代码再跑一次的时候,
#结果就不一样了,如果需要重复出现同样的模拟结果的话,
#就可以用set.seed()。在调试程序或者做展示的时候,
#结果的可重复性是很重要的,所以随机数种子也就很有必要。
#参考:https://blog.csdn.net/vencent_cy/article/details/50350020
wdata = data.frame(
sex = factor(rep(c("F", "M"), each=200)),
weight = c(rnorm(200, 55), rnorm(200, 58)))
head(wdata, 4) #设置一个数据框,包含sex因子,weight 向量,输出前5行
#> sex weight
#> 1 F 53.79293
#> 2 F 55.27743
#> 3 F 56.08444
#> 4 F 52.65430
# Density plot with mean lines and marginal rug
#密度分布图以及边际地毯线并添加平均值线
# :::::::::::::::::::::::::::::::::::::::::::::::::::
# Change outline and fill colors by groups ("sex") 按性别更改轮廓和填充颜色
# Use custom palette 使用自定义调色板
ggdensity(wdata, x = "weight",
add = "mean", rug = TRUE,
color = "sex", fill = "sex",
palette = c("#00AFBB", "#E7B800"))
# ggdensity绘图,设定x轴,添加平均线。
# rug =TRUE 是添加边缘地毯线,
# 如果rug=F,则不添加,可以看以下两张图的区别
分布图——直方图
# Histogram plot with mean lines and marginal rug
# 带有均值线和边际地毯线的直方图
# :::::::::::::::::::::::::::::::::::::::::::::::::::
# Change outline and fill colors by groups ("sex")
# Use custom color palette #使用自定义调色板
gghistogram(wdata, x = "weight",
add = "mean", rug = TRUE,
color = "sex", fill = "sex",
palette = c("#00AFBB", "#E7B800"))
其次:
箱线图及小提琴图—— 具有不同点分布的箱线图
# Load data 加载ToothGrowth数据,
# 它描述了维生素C对豚鼠牙齿生长的影响。
# 使用三种剂量水平的维生素C(0.5mg,1mg和2 mg)
# 和两种递送方法[橙汁(OJ)或抗坏血酸(VC)]中的每一种
data("ToothGrowth")
df <- ToothGrowth
head(df, 4) #输出前4行
#> len supp dose
#> 1 4.2 VC 0.5
#> 2 11.5 VC 0.5
#> 3 7.3 VC 0.5
#> 4 5.8 VC 0.5
# Box plots with jittered points
# :::::::::::::::::::::::::::::::::::::::::::::::::::
# Change outline colors by groups: dose
# Use custom color palette
# Add jitter points and change the shape by groups
p <- ggboxplot(df, x = "dose", y = "len",
color = "dose", palette =c("#00AFBB", "#E7B800", "#FC4E07"),
add = "jitter", shape = "dose")
p
# Add p-values comparing groups 每组添加p值
# Specify the comparisons you want 设置你想比较的任意组
my_comparisons <- list( c("0.5", "1"), c("1", "2"), c("0.5", "2") )
p + stat_compare_means(comparisons = my_comparisons)+ stat_compare_means(label.y = 50)
# Add pairwise comparisons p-value 添加成对p值
# Add global p-value 添加全局p值
箱线图及小提琴图—— 小提琴图内添加箱线图
# Violin plots with box plots inside
#小提琴图内添加箱线图
# :::::::::::::::::::::::::::::::::::::::::::::::::::
# Change fill color by groups: dose 以计量填充
# add boxplot with white fill color
ggviolin(df, x = "dose", y = "len", fill = "dose",
palette = c("#00AFBB", "#E7B800", "#FC4E07"), #颜色随机
add = "boxplot", add.params = list(fill = "white"))+ #添加内部箱线图
stat_compare_means(comparisons = my_comparisons, label = "p.signif")+
# Add significance levels 添加显著水平
stat_compare_means(label.y = 50)
# Add global the p-value 添加全局影响因子
第三
条形图—— 有序的条形图
# Load data 加载内置数据集 mtcars
data("mtcars")
dfm <- mtcars
# Convert the cyl variable to a factor 将cyl 变量转换为因子
dfm$cyl <- as.factor(dfm$cyl)
# Add the name colums 添加name列
dfm$name <- rownames(dfm)
# Inspect the data
head(dfm[, c("name", "wt", "mpg", "cyl")])
#> name wt mpg cyl
#> Mazda RX4 Mazda RX4 2.620 21.0 6
#> Mazda RX4 Wag Mazda RX4 Wag 2.875 21.0 6
#> Datsun 710 Datsun 710 2.320 22.8 4
#> Hornet 4 Drive Hornet 4 Drive 3.215 21.4 6
#> Hornet Sportabout Hornet Sportabout 3.440 18.7 8
#> Valiant Valiant 3.460 18.1 6
ggbarplot(dfm, x = "name", y = "mpg",
fill = "cyl", # change fill color by cyl
color = "white", # Set bar border colors to white
palette = "jco", # jco journal color palett. see ?ggpar
sort.val = "desc", # Sort the value in dscending order
sort.by.groups = FALSE, # Don't sort inside each group
不按组排序
x.text.angle = 90 # Rotate vertically x axis texts
)
ggbarplot(dfm, x = "name", y = "mpg",
fill = "cyl", # change fill color by cyl
color = "white", # Set bar border colors to white
palette = "jco", # jco journal color palett. see ?ggpar
sort.val = "asc", # Sort the value in dscending order
sort.by.groups = TRUE, # Sort inside each group 按组排序
x.text.angle = 90 # Rotate vertically x axis texts
)
条形图—— 偏差图
# Calculate the z-score of the mpg data
dfm$mpg_z <- (dfm$mpg -mean(dfm$mpg))/sd(dfm$mpg)
dfm$mpg_grp <- factor(ifelse(dfm$mpg_z < 0, "low", "high"),
levels = c("low", "high"))
# Inspect the data
head(dfm[, c("name", "wt", "mpg", "mpg_z", "mpg_grp", "cyl")])
#> name wt mpg mpg_z mpg_grp cyl
#> Mazda RX4 Mazda RX4 2.620 21.0 0.1508848 high 6
#> Mazda RX4 Wag Mazda RX4 Wag 2.875 21.0 0.1508848 high 6
#> Datsun 710 Datsun 710 2.320 22.8 0.4495434 high 4
#> Hornet 4 Drive Hornet 4 Drive 3.215 21.4 0.2172534 high 6
#> Hornet Sportabout Hornet Sportabout 3.440 18.7 -0.2307345 low 8
#> Valiant Valiant 3.460 18.1 -0.3302874 low 6
ggbarplot(dfm, x = "name", y = "mpg_z",
fill = "mpg_grp", # change fill color by mpg_level
color = "white", # Set bar border colors to white
palette = "jco", # jco journal color palett. see ?ggpar
sort.val = "asc", # Sort the value in ascending order
sort.by.groups = FALSE, # Don't sort inside each group
x.text.angle = 90, # Rotate vertically x axis texts
ylab = "MPG z-score",
xlab = FALSE,
legend.title = "MPG Group"
)
Rotate the plot: use rotate = TRUE and sort.val = “desc” 转换角度
ggbarplot(dfm, x = "name", y = "mpg_z",
fill = "mpg_grp", # change fill color by mpg_level
color = "white", # Set bar border colors to white
palette = "jco", # jco journal color palett. see ?ggpar
sort.val = "desc", # Sort the value in descending order
sort.by.groups = FALSE, # Don't sort inside each group
x.text.angle = 90, # Rotate vertically x axis texts
ylab = "MPG z-score",
legend.title = "MPG Group",
rotate = TRUE,
ggtheme = theme_minimal()
)
最后
点图——棒棒糖点图
ggdotchart(dfm, x = "name", y = "mpg",
color = "cyl", # Color by groups
palette = c("#00AFBB", "#E7B800", "#FC4E07"), # Custom color palette
sorting = "ascending", # Sort value in descending order
add = "segments", # Add segments from y = 0 to dots
ggtheme = theme_pubr() # ggplot2 theme
)
设置参数
- Sort in decending order. sorting = “descending”.
- Rotate the plot vertically, using rotate = TRUE.
- Sort the mpg value inside each group by using group = “cyl”.
- Set dot.size to 6.
- Add mpg values as label. label = “mpg” or label = round(dfm$mpg).
ggdotchart(dfm, x = "name", y = "mpg",
color = "cyl", # Color by groups
palette = c("#00AFBB", "#E7B800", "#FC4E07"), # Custom color palette
sorting = "descending", # Sort value in descending order
add = "segments", # Add segments from y = 0 to dots
rotate = TRUE, # Rotate vertically
group = "cyl", # Order by groups
dot.size = 6, # Large dot size
label = round(dfm$mpg), # Add mpg values as dot labels
font.label = list(color = "white", size = 9,
vjust = 0.5), # Adjust label parameters
ggtheme = theme_pubr() # ggplot2 theme
)
**点图——偏差图
- Use y = “mpg_z”
- Change segment color and size: add.params = list(color = “lightgray”, size = 2)
ggdotchart(dfm, x = "name", y = "mpg_z",
color = "cyl", # Color by groups
palette = c("#00AFBB", "#E7B800", "#FC4E07"), # Custom color palette
sorting = "descending", # Sort value in descending order
add = "segments", # Add segments from y = 0 to dots
add.params = list(color = "lightgray", size = 2), # Change segment color and size
group = "cyl", # Order by groups
dot.size = 6, # Large dot size
label = round(dfm$mpg_z,1), # Add mpg values as dot labels
font.label = list(color = "white", size = 9,
vjust = 0.5), # Adjust label parameters
ggtheme = theme_pubr() # ggplot2 theme
)+
geom_hline(yintercept = 0, linetype = 2, color = "lightgray")
Color y text by groups. Use y.text.col = TRUE.
ggdotchart(dfm, x = "name", y = "mpg",
color = "cyl", # Color by groups
palette = c("#00AFBB", "#E7B800", "#FC4E07"), # Custom color palette
sorting = "descending", # Sort value in descending order
rotate = TRUE, # Rotate vertically
dot.size = 2, # Large dot size
y.text.col = TRUE, # Color y text by groups
ggtheme = theme_pubr() # ggplot2 theme
)+
theme_cleveland() # Add dashed grids
以上 。
入门生信最快方式请搜索生信技能树
- 生信技能树全球公益巡讲
https://mp.weixin.qq.com/s/E9ykuIbc-2Ja9HOY0bn_6g - B站公益74小时生信工程师教学视频合辑https://mp.weixin.qq.com/s/IyFK7l_WBAiUgqQi8O7Hxw
- 招学徒
https://mp.weixin.qq.com/s/KgbilzXnFjbKKunuw7NVfw