【原】箱线图和小提琴图合在一起更好

微生信生物 2021-01-16

展开全文

Boxplot

一般我们的箱线图就是这样

# Libraries
library(tidyverse)
library(hrbrthemes)
library(viridis)

# create a dataset
data <- data.frame(
  name=c( rep("A",500), rep("B",500), rep("B",500), rep("C",20), rep('D', 100)  ),
  value=c( rnorm(500, 10, 5), rnorm(500, 13, 1), rnorm(500, 18, 1), rnorm(20, 25, 4), rnorm(100, 12, 1) )
)


# Boxplot basic
data %>%
  ggplot( aes(x=name, y=value, fill=name)) +
    geom_boxplot() +
    scale_fill_viridis(discrete = TRUE, alpha=0.6, option="A") +
    theme_ipsum() +
    theme(
      legend.position="none",
      plot.title = element_text(size=11)
    ) +
    ggtitle("Basic boxplot") +
    xlab("")

给他加上geom_jitter：离样本点撒到上面

# Plot
data %>%
  ggplot( aes(x=name, y=value, fill=name)) +
    geom_boxplot() +
    scale_fill_viridis(discrete = TRUE, alpha=0.6) +
    geom_jitter(color="black", size=0.4, alpha=0.9) +
    theme_ipsum() +
    theme(
      legend.position="none",
      plot.title = element_text(size=11)
    ) +
    ggtitle("A boxplot with jitter") +
    xlab("")

将箱子换成小提琴：geom_violin

# Violin basic
data %>%
  ggplot( aes(x=name, y=value, fill=name)) +
    geom_violin() +
    scale_fill_viridis(discrete = TRUE, alpha=0.6, option="A") +
    theme_ipsum() +
    theme(
      legend.position="none",
      plot.title = element_text(size=11)
    ) +
    ggtitle("Violin chart") +
    xlab("")

# Load ggplot2
library(ggplot2)
 
# The mpg dataset is natively available
#head(mpg)
 
# geom_boxplot proposes several arguments to custom appearance
ggplot(mpg, aes(x=class, y=hwy)) +
    geom_boxplot(
        
        # custom boxes
        color="blue",
        fill="blue",
        alpha=0.2,
        
        # Notch?
        notch=TRUE,
        notchwidth = 0.8,
        
        # custom outliers
        outlier.colour="red",
        outlier.fill="red",
        outlier.size=3
    
    )

大部分人都不知道：如何映射箱子粗细，使用:varwidth = TRUE

# library
library(ggplot2)
 
# create data
names <- c(rep("A", 20) , rep("B", 5) , rep("C", 30), rep("D", 100))
value <- c( sample(2:5, 20 , replace=T) , sample(4:10, 5 , replace=T), sample(1:7, 30 , replace=T), sample(3:8, 100 , replace=T) )
data <- data.frame(names,value)
 
# prepare a special xlab with the number of obs for each group
my_xlab <- paste(levels(data$names),"\n(N=",table(data$names),")",sep="")
 
# plot
ggplot(data, aes(x=names, y=value, fill=names)) +
    geom_boxplot(varwidth = TRUE, alpha=0.2) +
    theme(legend.position="none") +
    scale_x_discrete(labels=my_xlab)

小提琴和箱线图还是放一起的好

# Libraries
library(ggplot2)
library(dplyr)
library(hrbrthemes)
library(viridis)

# create a dataset
data <- data.frame(
  name=c( rep("A",500), rep("B",500), rep("B",500), rep("C",20), rep('D', 100)  ),
  value=c( rnorm(500, 10, 5), rnorm(500, 13, 1), rnorm(500, 18, 1), rnorm(20, 25, 4), rnorm(100, 12, 1) )
)

# sample size
sample_size = data %>% group_by(name) %>% summarize(num=n())

# Plot
data %>%
  left_join(sample_size) %>%
  mutate(myaxis = paste0(name, "\n", "n=", num)) %>%
  ggplot( aes(x=myaxis, y=value, fill=name)) +
    geom_violin(width=1.4) +
    geom_boxplot(width=0.1, color="grey", alpha=0.2) +
    scale_fill_viridis(discrete = TRUE) +
    theme_ipsum() +
    theme(
      legend.position="none",
      plot.title = element_text(size=11)
    ) +
    ggtitle("A Violin wrapping a boxplot") +
    xlab("")